Deyi Xiong

Also published as: De-Yi Xiong


2023

pdf bib
X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents
Mehrad Moradshahi | Tianhao Shen | Kalika Bali | Monojit Choudhury | Gael de Chalendar | Anmol Goel | Sungkyun Kim | Prashant Kodali | Ponnurangam Kumaraguru | Nasredine Semmar | Sina Semnani | Jiwon Seo | Vivek Seshadri | Manish Shrivastava | Michael Sun | Aditya Yadavalli | Chaobin You | Deyi Xiong | Monica Lam
Findings of the Association for Computational Linguistics: ACL 2023

Task-oriented dialogue research has mainly focused on a few popular languages like English and Chinese, due to the high dataset creation cost for a new language. To reduce the cost, we apply manual editing to automatically translated data. We create a new multilingual benchmark, X-RiSAWOZ, by translating the Chinese RiSAWOZ to 4 languages: English, French, Hindi, Korean; and a code-mixed English-Hindi language.X-RiSAWOZ has more than 18,000 human-verified dialogue utterances for each language, and unlike most multilingual prior work, is an end-to-end dataset for building fully-functioning agents. The many difficulties we encountered in creating X-RiSAWOZ led us to develop a toolset to accelerate the post-editing of a new language dataset after translation. This toolset improves machine translation with a hybrid entity alignment technique that combines neural with dictionary-based methods, along with many automated and semi-automated validation checks. We establish strong baselines for X-RiSAWOZ by training dialogue agents in the zero- and few-shot settings where limited gold data is available in the target language. Our results suggest that our translation and post-editing methodology and toolset can be used to create new high-quality multilingual dialogue agents cost-effectively. Our dataset, code, and toolkit are released open-source.

pdf bib
CKDST: Comprehensively and Effectively Distill Knowledge from Machine Translation to End-to-End Speech Translation
Yikun Lei | Zhengshan Xue | Xiaohu Zhao | Haoran Sun | Shaolin Zhu | Xiaodong Lin | Deyi Xiong
Findings of the Association for Computational Linguistics: ACL 2023

Distilling knowledge from a high-resource task, e.g., machine translation, is an effective way to alleviate the data scarcity problem of end-to-end speech translation. However, previous works simply use the classical knowledge distillation that does not allow for adequate transfer of knowledge from machine translation. In this paper, we propose a comprehensive knowledge distillation framework for speech translation, CKDST, which is capable of comprehensively and effectively distilling knowledge from machine translation to speech translation from two perspectives: cross-modal contrastive representation distillation and simultaneous decoupled knowledge distillation. In the former, we leverage a contrastive learning objective to optmize the mutual information between speech and text representations for representation distillation in the encoder. In the later, we decouple the non-target class knowledge from target class knowledge for logits distillation in the decoder. Experiments on the MuST-C benchmark dataset demonstrate that our CKDST substantially improves the baseline by 1.2 BLEU on average in all translation directions, and outperforms previous state-of-the-art end-to-end and cascaded speech translation models.

pdf bib
HuaSLIM: Human Attention Motivated Shortcut Learning Identification and Mitigation for Large Language models
Yuqi Ren | Deyi Xiong
Findings of the Association for Computational Linguistics: ACL 2023

Large language models have made remarkable progress on a variety of NLP tasks. However, it has been found that they tend to rely on shortcut features that spuriously correlate with labels for prediction, which weakens their generalization on out-of-distribution samples. In this paper, we propose a human attention guided approach to identifying and mitigating shortcut learning, which encourages the LLM-based target model to learn relevant features. We define an attention-based measurement to capture both model and data bias and identify shortcut tokens by exploring both human and neural attention. In a self-distillation framework, we mitigate shortcut learning by dynamically adjusting the distillation temperature according to the detected shortcut tokens and estimated shortcut degree. Additionally, we utilize human attention as a supervisory signal to constrain large language models to pay more attention to relevant tokens. Experimental results on multiple NLP tasks show that our proposed method can effectively identify shortcut tokens, and significantly improve the robustness of large language models on OOD samples, while not undermining the performance on IID data.

pdf bib
CCSRD: Content-Centric Speech Representation Disentanglement Learning for End-to-End Speech Translation
Xiaohu Zhao | Haoran Sun | Yikun Lei | Shaolin Zhu | Deyi Xiong
Findings of the Association for Computational Linguistics: EMNLP 2023

Deep neural networks have demonstrated their capacity in extracting features from speech inputs. However, these features may include non-linguistic speech factors such as timbre and speaker identity, which are not directly related to translation. In this paper, we propose a content-centric speech representation disentanglement learning framework for speech translation, CCSRD, which decomposes speech representations into content representations and non-linguistic representations via representation disentanglement learning. CCSRD consists of a content encoder that encodes linguistic content information from the speech input, a non-content encoder that models non-linguistic speech features, and a disentanglement module that learns disentangled representations with a cyclic reconstructor, feature reconstructor and speaker classifier trained in a multi-task learning way. Experiments on the MuST-C benchmark dataset demonstrate that CCSRD achieves an average improvement of +0.9 BLEU in two settings across five translation directions over the baseline, outperforming state-of-the-art end-to-end speech translation models and cascaded models.

pdf bib
Inverse Reinforcement Learning for Text Summarization
Yu Fu | Deyi Xiong | Yue Dong
Findings of the Association for Computational Linguistics: EMNLP 2023

We introduce inverse reinforcement learning (IRL) as an effective paradigm for training abstractive summarization models, imitating human summarization behaviors. Our IRL model estimates the reward function using a suite of important sub-rewards for summarization and concurrently optimizes the policy network. Experimental results across datasets in different domains (CNN/DailyMail and WikiHow) and various model sizes (BART-base and BART-large) demonstrate the superiority of our proposed IRL model for summarization over MLE and RL baselines. The resulting summaries exhibit greater similarity to human-crafted gold references, outperforming MLE and RL baselines on metrics such as ROUGE, coverage, novelty, compression ratio, factuality, and human evaluations.

pdf bib
Is Robustness Transferable across Languages in Multilingual Neural Machine Translation?
Leiyu Pan | Supryadi | Deyi Xiong
Findings of the Association for Computational Linguistics: EMNLP 2023

Robustness, the ability of models to maintain performance in the face of perturbations, is critical for developing reliable NLP systems. Recent studies have shown promising results in improving the robustness of models through adversarial training and data augmentation. However, in machine translation, most of these studies have focused on bilingual machine translation with a single translation direction. In this paper, we investigate the transferability of robustness across different languages in multilingual neural machine translation. We propose a robustness transfer analysis protocol and conduct a series of experiments. In particular, we use character-, word-, and multi-level noises to attack the specific translation direction of the multilingual neural machine translation model and evaluate the robustness of other translation directions. Our findings demonstrate that the robustness gained in one translation direction can indeed transfer to other translation directions. Additionally, we empirically find scenarios where robustness to character-level noise and word-level noise is more likely to transfer.

pdf bib
Towards a Deep Understanding of Multilingual End-to-End Speech Translation
Haoran Sun | Xiaohu Zhao | Yikun Lei | Shaolin Zhu | Deyi Xiong
Findings of the Association for Computational Linguistics: EMNLP 2023

In this paper, we employ Singular Value Canonical Correlation Analysis (SVCCA) to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages. SVCCA enables us to estimate representational similarity across languages and layers, enhancing our understanding of the functionality of multilingual speech translation and its potential connection to multilingual neural machine translation. The multilingual speech translation model is trained on the CoVoST 2 dataset in all possible directions, and we utilize LASER to extract parallel bitext data for SVCCA analysis. We derive three major findings from our analysis: (I) Linguistic similarity loses its efficacy in multilingual speech translation when the training data for a specific language is limited. (II) Enhanced encoder representations and well-aligned audio-text data significantly improve translation quality, surpassing the bilingual counterparts when the training data is not compromised. (III) The encoder representations of multilingual speech translation demonstrate superior performance in predicting phonetic features in linguistic typology prediction. With these findings, we propose that releasing the constraint of limited data for low-resource languages and subsequently combining them with linguistically related high-resource languages could offer a more effective approach for multilingual end-to-end speech translation.

pdf bib
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
Xinwei Wu | Junzhuo Li | Minghui Xu | Weilong Dong | Shuangzhi Wu | Chao Bian | Deyi Xiong
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Pretrained language models have learned a vast amount of human knowledge from large-scale corpora, but their powerful memorization capability also brings the risk of data leakage. Some risks may only be discovered after the model training is completed, such as the model memorizing a specific phone number and frequently outputting it. In such cases, model developers need to eliminate specific data influences from the model to mitigate legal and ethical penalties. To effectively mitigate these risks, people often have to spend a significant amount of time and computational costs to retrain new models instead of finding ways to cure the ‘sick’ models. Therefore, we propose a method to locate and erase risky neurons in order to eliminate the impact of privacy data in the model. We use a new method based on integrated gradients to locate neurons associated with privacy texts, and then erase these neurons by setting their activation values to zero.Furthermore, we propose a risky neuron aggregation method to eliminate the influence of privacy data in the model in batches. Experimental results show that our method can effectively and quickly eliminate the impact of privacy data without affecting the model’s performance. Additionally, we demonstrate the relationship between model memorization and neurons through experiments, further illustrating the robustness of our method.

pdf bib
Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?
Shaoyang Xu | Junzhuo Li | Deyi Xiong
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Multilingual pretrained language models serve as repositories of multilingual factual knowledge. Nevertheless, a substantial performance gap of factual knowledge probing exists between high-resource languages and low-resource languages, suggesting limited implicit factual knowledge transfer across languages in multilingual pretrained language models. This paper investigates the feasibility of explicitly transferring relatively rich factual knowledge from English to non-English languages. To accomplish this, we propose two parameter-free Language Representation Projection modules (LRP2). The first module converts non-English representations into English-like equivalents, while the second module reverts English-like representations back into representations of the corresponding non-English language. Experimental results on the mLAMA dataset demonstrate that LRP2 significantly improves factual knowledge retrieval accuracy and facilitates knowledge transferability across diverse non-English languages. We further investigate the working mechanism of LRP2 from the perspectives of representation space and cross-lingual knowledge neuron.

pdf bib
CS2W: A Chinese Spoken-to-Written Style Conversion Dataset with Multiple Conversion Types
Zishan Guo | Linhao Yu | Minghui Xu | Renren Jin | Deyi Xiong
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Spoken texts (either manual or automatic transcriptions from automatic speech recognition (ASR)) often contain disfluencies and grammatical errors, which pose tremendous challenges to downstream tasks. Converting spoken into written language is hence desirable. Unfortunately, the availability of datasets for this is limited. To address this issue, we present CS2W, a Chinese Spoken-to-Written style conversion dataset comprising 7,237 spoken sentences extracted from transcribed conversational texts. Four types of conversion problems are covered in CS2W: disfluencies, grammatical errors, ASR transcription errors, and colloquial words. Our annotation convention, data, and code are publicly available at https://github.com/guozishan/CS2W.

pdf bib
MMNMT: Modularizing Multilingual Neural Machine Translation with Flexibly Assembled MoE and Dense Blocks
Shangjie Li | Xiangpeng Wei | Shaolin Zhu | Jun Xie | Baosong Yang | Deyi Xiong
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Mixture-of-Experts (MoE) based sparse architectures can significantly increase model capacity with sublinear computational overhead, which are hence widely used in massively multilingual neural machine translation (MNMT). However, they are prone to overfitting on low-resource language translation. In this paper, we propose a modularized MNMT framework that is able to flexibly assemble dense and MoE-based sparse modules to achieve the best of both worlds. The training strategy of the modularized MNMT framework consists of three stages: (1) Pre-training basic MNMT models with different training objectives or model structures, (2) Initializing modules of the framework with pre-trained couterparts (e.g., encoder, decoder and embedding layers) from the basic models and (3) Fine-tuning the modularized MNMT framework to fit modules from different models together. We pre-train three basic MNMT models from scratch: a dense model, an MoE-based sparse model and a new MoE model, termed as MoE-LGR that explores multiple Language-Group-specifc Routers to incorporate language group knowledge into MNMT. The strengths of these pre-trained models are either on low-resource language translation, high-resource language translation or zero-shot translation. Our modularized MNMT framework attempts to incorporate these advantages into a single model with reasonable initialization and fine-tuning. Experiments on widely-used benchmark datasets demonstrate that the proposed modularized MNMT framwork substantially outperforms both MoE and dense models on high- and low-resource language translation as well as zero-shot translation. Our framework facilitates the combination of different methods with their own strengths and recycling off-the-shelf models for multilingual neural machine translation. Codes are available at https://github.com/lishangjie1/MMNMT.

pdf bib
TJUNLP:System Description for the WMT23 Literary Task in Chinese to English Translation Direction
Shaolin Zhu | Deyi Xiong
Proceedings of the Eighth Conference on Machine Translation

This paper introduces the overall situation of the Natural Language Processing Laboratory of Tianjin University participating in the WMT23 machine translation evaluation task from Chinese to English. For this evaluation, the base model used is a Transformer based on a Mixture of Experts (MOE) model. During the model’s construction and training, a basic dense model based on Transformer is first trained on the training set. Then, this model is used to initialize the MOE-based translation model, which is further trained on the training corpus. Since the training dataset provided for this translation task is relatively small, to better utilize sparse models to enhance translation, we employed a data augmentation technique for alignment. Experimental results show that this method can effectively improve neural machine translation performance.

pdf bib
PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image Translation
Shaolin Zhu | Shangjie Li | Yikun Lei | Deyi Xiong
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Image translation is a task that translates an image containing text in the source language to the target language. One major challenge with image translation is the modality gap between visual text inputs and textual inputs/outputs of machine translation (MT). In this paper, we propose PEIT, an end-to-end image translation framework that bridges the modality gap with pre-trained models. It is composed of four essential components: a visual encoder, a shared encoder-decoder backbone network, a vision-text representation aligner equipped with the shared encoder and a cross-modal regularizer stacked over the shared decoder. Both the aligner and regularizer aim at reducing the modality gap. To train PEIT, we employ a two-stage pre-training strategy with an auxiliary MT task: (1) pre-training the MT model on the MT training data to initialize the shared encoder-decoder backbone network; and (2) pre-training PEIT with the aligner and regularizer on a synthesized dataset with rendered images containing text from the MT training data. In order to facilitate the evaluation of PEIT and promote research on image translation, we create a large-scale image translation corpus ECOIT containing 480K image-translation pairs via crowd-sourcing and manual post-editing from real-world images in the e-commerce domain. Experiments on the curated ECOIT benchmark dataset demonstrate that PEIT substantially outperforms both cascaded image translation systems (OCR+MT) and previous strong end-to-end image translation model, with fewer parameters and faster decoding speed.

pdf bib
Tab-CQA: A Tabular Conversational Question Answering Dataset on Financial Reports
Chuang Liu | Junzhuo Li | Deyi Xiong
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)

Existing conversational question answering (CQA) datasets have been usually constructed from unstructured texts in English. In this paper, we propose Tab-CQA, a tabular CQA dataset created from Chinese financial reports that are extracted from listed companies in a wide range of different sectors in the past 30 years. From these reports, we select 2,463 tables, and manually generate 2,463 conversations with 35,494 QA pairs. Additionally, we select 4,578 tables, from which 4,578 conversations with 73,595 QA pairs are automatically created via a template-based method. With the manually- and automatically-generated conversations, Tab-CQA contains answerable and unanswerable questions. For the answerable questions, we further diversify them to cover a wide range of skills, e.g., table retrieval, fact checking, numerical reasoning, so as to accommodate real-world scenarios. We further propose two different tabular CQA models, a text-based model and an operation-based model, and evaluate them on Tab-CQA. Experiment results show that Tab-CQA is a very challenging dataset, where a huge performance gap exists between human and neural models. We will publicly release Tab-CQA as a benchmark testbed to promote further research on Chinese tabular CQA.

2022

pdf bib
Learning Structural Information for Syntax-Controlled Paraphrase Generation
Erguang Yang | Chenglin Bai | Deyi Xiong | Yujie Zhang | Yao Meng | Jinan Xu | Yufeng Chen
Findings of the Association for Computational Linguistics: NAACL 2022

Syntax-controlled paraphrase generation aims to produce paraphrase conform to given syntactic patterns. To address this task, recent works have started to use parse trees (or syntactic templates) to guide generation.A constituency parse tree contains abundant structural information, such as parent-child relation, sibling relation, and the alignment relation between words and nodes. Previous works have only utilized parent-child and alignment relations, which may affect the generation quality. To address this limitation, we propose a Structural Information-augmented Syntax-Controlled Paraphrasing (SI-SCP) model. Particularly, we design a syntax encoder based on tree-transformer to capture parent-child and sibling relations. To model the alignment relation between words and nodes, we propose an attention regularization objective, which makes the decoder accurately select corresponding syntax nodes to guide the generation of words. Experiments show that SI-SCP achieves state-of-the-art performances in terms of semantic and syntactic quality on two popular benchmark datasets. Additionally, we propose a Syntactic Template Retriever (STR) to retrieve compatible syntactic structures. We validate that STR is capable of retrieving compatible syntactic structures. We further demonstrate the effectiveness of SI-SCP to generate diverse paraphrases with retrieved syntactic structures.

pdf bib
Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets
Shuaibo Wang | Yufeng Chen | Songming Zhang | Deyi Xiong | Jinan Xu
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Neural machine translation (NMT) models are known to be fragile to noisy inputs from automatic speech recognition (ASR) systems. Existing methods are usually tailored for robustness against only homophone errors which account for a small portion of realistic ASR errors. In this paper, we propose an adversarial example generation method based on confusion sets that contain words easily confusable with a target word by ASR to conduct adversarial training for NMT models. Specifically, an adversarial example is generated from the perspective of acoustic relations instead of the traditional uniform or unigram sampling from the confusion sets. Experiments on different test sets with hand-crafted and real-world noise demonstrate the effectiveness of our method over previous methods. Moreover, our approach can achieve improvements on the clean test set.

pdf bib
Evaluating Discourse Cohesion in Pre-trained Language Models
Jie He | Wanqiu Long | Deyi Xiong
Proceedings of the 3rd Workshop on Computational Approaches to Discourse

Large pre-trained neural models have achieved remarkable success in natural language process (NLP), inspiring a growing body of research analyzing their ability from different aspects. In this paper, we propose a test suite to evaluate the cohesive ability of pre-trained language models. The test suite contains multiple cohesion phenomena between adjacent and non-adjacent sentences. We try to compare different pre-trained language models on these phenomena and analyze the experimental results,hoping more attention can be given to discourse cohesion in the future. The built discourse cohesion test suite will be publicly available at https://github.com/probe2/discourse_cohesion.

pdf bib
Adaptive Differential Privacy for Language Model Training
Xinwei Wu | Li Gong | Deyi Xiong
Proceedings of the First Workshop on Federated Learning for Natural Language Processing (FL4NLP 2022)

Although differential privacy (DP) can protect language models from leaking privacy, its indiscriminative protection on all data points reduces its practical utility. Previous works improve DP training by discriminating privacy and non-privacy data. But these works rely on datasets with prior privacy information, which is not available in real-world scenarios. In this paper, we propose an Adaptive Differential Privacy (ADP) framework for language modeling without resorting to prior privacy information. We estimate the probability that a linguistic item contains privacy based on a language model. We further propose a new Adam algorithm that adjusts the degree of differential privacy noise injected to the language model according to the estimated privacy probabilities. Experiments demonstrate that our ADP improves differentially private language modeling to achieve good protection from canary attackers.

pdf bib
KaFSP: Knowledge-Aware Fuzzy Semantic Parsing for Conversational Question Answering over a Large-Scale Knowledge Base
Junzhuo Li | Deyi Xiong
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In this paper, we study two issues of semantic parsing approaches to conversational question answering over a large-scale knowledge base: (1) The actions defined in grammar are not sufficient to handle uncertain reasoning common in real-world scenarios. (2) Knowledge base information is not well exploited and incorporated into semantic parsing. To mitigate the two issues, we propose a knowledge-aware fuzzy semantic parsing framework (KaFSP). It defines fuzzy comparison operations in the grammar system for uncertain reasoning based on the fuzzy set theory. In order to enhance the interaction between semantic parsing and knowledge base, we incorporate entity triples from the knowledge base into a knowledge-aware entity disambiguation module. Additionally, we propose a multi-label classification framework to not only capture correlations between entity types and relations but also detect knowledge base information relevant to the current utterance. Both enhancements are based on pre-trained language models. Experiments on a large-scale conversational question answering benchmark demonstrate that the proposed KaFSP achieves significant improvements over previous state-of-the-art models, setting new SOTA results on 8 out of 10 question types, gaining improvements of over 10% F1 or accuracy on 3 question types, and improving overall F1 from 83.01% to 85.33%. The source code of KaFSP is available at https://github.com/tjunlp-lab/KaFSP.

pdf bib
CogTaskonomy: Cognitively Inspired Task Taxonomy Is Beneficial to Transfer Learning in NLP
Yifei Luo | Minghui Xu | Deyi Xiong
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Is there a principle to guide transfer learning across tasks in natural language processing (NLP)? Taxonomy (Zamir et al., 2018) finds that a structure exists among visual tasks, as a principle underlying transfer learning for them. In this paper, we propose a cognitively inspired framework, CogTaskonomy, to learn taxonomy for NLP tasks. The framework consists of Cognitive Representation Analytics (CRA) and Cognitive-Neural Mapping (CNM). The former employs Representational Similarity Analysis, which is commonly used in computational neuroscience to find a correlation between brain-activity measurement and computational modeling, to estimate task similarity with task-specific sentence representations. The latter learns to detect task relations by projecting neural representations from NLP models to cognitive signals (i.e., fMRI voxels). Experiments on 12 NLP tasks, where BERT/TinyBERT are used as the underlying models for transfer learning, demonstrate that the proposed CogTaxonomy is able to guide transfer learning, achieving performance competitive to the Analytic Hierarchy Process (Saaty, 1987) used in visual Taskonomy (Zamir et al., 2018) but without requiring exhaustive pairwise O(m2) task transferring. Analyses further discover that CNM is capable of learning model-agnostic task taxonomy.

pdf bib
Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension
Linjuan Wu | Shaojuan Wu | Xiaowang Zhang | Deyi Xiong | Shizhan Chen | Zhiqiang Zhuang | Zhiyong Feng
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Multilingual pre-trained models are able to zero-shot transfer knowledge from rich-resource to low-resource languages in machine reading comprehension (MRC). However, inherent linguistic discrepancies in different languages could make answer spans predicted by zero-shot transfer violate syntactic constraints of the target language. In this paper, we propose a novel multilingual MRC framework equipped with a Siamese Semantic Disentanglement Model (S2DM) to disassociate semantics from syntax in representations learned by multilingual pre-trained models. To explicitly transfer only semantic knowledge to the target language, we propose two groups of losses tailored for semantic and syntactic encoding and disentanglement. Experimental results on three multilingual MRC datasets (i.e., XQuAD, MLQA, and TyDi QA) demonstrate the effectiveness of our proposed approach over models based on mBERT and XLM-100.

pdf bib
Efficient Cluster-Based k-Nearest-Neighbor Machine Translation
Dexin Wang | Kai Fan | Boxing Chen | Deyi Xiong
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

k-Nearest-Neighbor Machine Translation (kNN-MT) has been recently proposed as a non-parametric solution for domain adaptation in neural machine translation (NMT). It aims to alleviate the performance degradation of advanced MT systems in translating out-of-domain sentences by coordinating with an additional token-level feature-based retrieval module constructed from in-domain data. Previous studies (Khandelwal et al., 2021; Zheng et al., 2021) have already demonstrated that non-parametric NMT is even superior to models fine-tuned on out-of-domain data. In spite of this success, kNN retrieval is at the expense of high latency, in particular for large datastores. To make it practical, in this paper, we explore a more efficient kNN-MT and propose to use clustering to improve the retrieval efficiency. Concretely, we first propose a cluster-based Compact Network for feature reduction in a contrastive learning manner to compress context features into 90+% lower dimensional vectors. We then suggest a cluster-based pruning solution to filter out 10% 40% redundant nodes in large datastores while retaining translation quality. Our proposed methods achieve better or comparable performance while reducing up to 57% inference latency against the advanced non-parametric MT model on several machine translation benchmarks. Experimental results indicate that the proposed methods maintain the most useful information of the original datastore and the Compact Network shows good generalization on unseen domains. Codes are available at https://github.com/tjunlp-lab/PCKMT.

pdf bib
ParaZh-22M: A Large-Scale Chinese Parabank via Machine Translation
Wenjie Hao | Hongfei Xu | Deyi Xiong | Hongying Zan | Lingling Mu
Proceedings of the 29th International Conference on Computational Linguistics

Paraphrasing, i.e., restating the same meaning in different ways, is an important data augmentation approach for natural language processing (NLP). Zhang et al. (2019b) propose to extract sentence-level paraphrases from multiple Chinese translations of the same source texts, and construct the PKU Paraphrase Bank of 0.5M sentence pairs. However, despite being the largest Chinese parabank to date, the size of PKU parabank is limited by the availability of one-to-many sentence translation data, and cannot well support the training of large Chinese paraphrasers. In this paper, we relieve the restriction with one-to-many sentence translation data, and construct ParaZh-22M, a larger Chinese parabank that is composed of 22M sentence pairs, based on one-to-one bilingual sentence translation data and machine translation (MT). In our data augmentation experiments, we show that paraphrasing based on ParaZh-22M can bring about consistent and significant improvements over several strong baselines on a wide range of Chinese NLP tasks, including a number of Chinese natural language understanding benchmarks (CLUE) and low-resource machine translation.

pdf bib
Language Branch Gated Multilingual Neural Machine Translation
Haoran Sun | Deyi Xiong
Proceedings of the 29th International Conference on Computational Linguistics

Knowledge transfer across languages is crucial for multilingual neural machine translation. In this paper, we propose language branch (LB) gated multilingual neural machine translation that encourages knowledge transfer within the same language branch with a LB-gated module that is integrated into both the encoder and decoder. The LB-gated module distinguishes LB-specific parameters from global parameters shared by all languages and routes languages from the same LB to the corresponding LB-specific network. Comprehensive experiments on the OPUS-100 dataset show that the proposed approach substantially improves translation quality on both middle- and low-resource languages over previous methods. Further analysis demonstrates its ability in learning similarities between language branches.

pdf bib
Informative Language Representation Learning for Massively Multilingual Neural Machine Translation
Renren Jin | Deyi Xiong
Proceedings of the 29th International Conference on Computational Linguistics

In a multilingual neural machine translation model that fully shares parameters across all languages, an artificial language token is usually used to guide translation into the desired target language. However, recent studies show that prepending language tokens sometimes fails to navigate the multilingual neural machine translation models into right translation directions, especially on zero-shot translation. To mitigate this issue, we propose two methods, language embedding embodiment and language-aware multi-head attention, to learn informative language representations to channel translation into right directions. The former embodies language embeddings into different critical switching points along the information flow from the source to the target, aiming at amplifying translation direction guiding signals. The latter exploits a matrix, instead of a vector, to represent a language in the continuous space. The matrix is chunked into multiple heads so as to learn language representations in multiple subspaces. Experiment results on two datasets for massively multilingual neural machine translation demonstrate that language-aware multi-head attention benefits both supervised and zero-shot translation and significantly alleviates the off-target translation issue. Further linguistic typology prediction experiments show that matrix-based language representations learned by our methods are capable of capturing rich linguistic typology features.

pdf bib
CoDoNMT: Modeling Cohesion Devices for Document-Level Neural Machine Translation
Yikun Lei | Yuqi Ren | Deyi Xiong
Proceedings of the 29th International Conference on Computational Linguistics

Cohesion devices, e.g., reiteration, coreference, are crucial for building cohesion links across sentences. In this paper, we propose a document-level neural machine translation framework, CoDoNMT, which models cohesion devices from two perspectives: Cohesion Device Masking (CoDM) and Cohesion Attention Focusing (CoAF). In CoDM, we mask cohesion devices in the current sentence and force NMT to predict them with inter-sentential context information. A prediction task is also introduced to be jointly trained with NMT. In CoAF, we attempt to guide the model to pay exclusive attention to relevant cohesion devices in the context when translating cohesion devices in the current sentence. Such a cohesion attention focusing strategy is softly applied to the self-attention layer. Experiments on three benchmark datasets demonstrate that our approach outperforms state-of-the-art document-level neural machine translation baselines. Further linguistic evaluation validates the effectiveness of the proposed model in producing cohesive translations.

pdf bib
Long Text Generation with Topic-aware Discrete Latent Variable Model
Erguang Yang | Mingtong Liu | Deyi Xiong | Yujie Zhang | Yufeng Chen | Jinan Xu
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Generating coherent long texts is an important yet challenging task, particularly forthe open-ended generation. Prior work based on discrete latent codes focuses on the modeling of discourse relation, resulting in discrete codes only learning shallow semantics (Ji and Huang, 2021). A natural text always revolves around several related topics and the transition across them is natural and smooth. In this work, we investigate whether discrete latent codes can learn information of topics. To this end, we build a topic-aware latent code-guided text generation model. To encourage discrete codes to model information about topics, we propose a span-level bag-of-words training objective for the model. Automatic and manual evaluation experiments show that our method can generate more topic-relevant and coherent texts.

pdf bib
Recovering Gold from Black Sand: Multilingual Dense Passage Retrieval with Hard and False Negative Samples
Tianhao Shen | Mingtong Liu | Ming Zhou | Deyi Xiong
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Negative samples have not been efficiently explored in multilingual dense passage retrieval. In this paper, we propose a novel multilingual dense passage retrieval framework, mHFN, to recover and utilize hard and false negative samples. mHFN consists of three key components: 1) a multilingual hard negative sample augmentation module that allows knowledge of indistinguishable passages to be shared across multiple languages and synthesizes new hard negative samples by interpolating representations of queries and existing hard negative samples, 2) a multilingual negative sample cache queue that stores negative samples from previous batches in each language to increase the number of multilingual negative samples used in training beyond the batch size limit, and 3) a lightweight adaptive false negative sample filter that uses generated pseudo labels to separate unlabeled false negative samples and converts them into positive passages in training. We evaluate mHFN on Mr. TyDi, a high-quality multilingual dense passage retrieval dataset covering eleven typologically diverse languages, and experimental results show that mHFN outperforms strong sparse, dense and hybrid baselines and achieves new state-of-the-art performance on all languages. Our source code is available at https://github.com/Magnetic2014/mHFN.

pdf bib
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
Sebastian Gehrmann | Abhik Bhattacharjee | Abinaya Mahendiran | Alex Wang | Alexandros Papangelis | Aman Madaan | Angelina Mcmillan-major | Anna Shvets | Ashish Upadhyay | Bernd Bohnet | Bingsheng Yao | Bryan Wilie | Chandra Bhagavatula | Chaobin You | Craig Thomson | Cristina Garbacea | Dakuo Wang | Daniel Deutsch | Deyi Xiong | Di Jin | Dimitra Gkatzia | Dragomir Radev | Elizabeth Clark | Esin Durmus | Faisal Ladhak | Filip Ginter | Genta Indra Winata | Hendrik Strobelt | Hiroaki Hayashi | Jekaterina Novikova | Jenna Kanerva | Jenny Chim | Jiawei Zhou | Jordan Clive | Joshua Maynez | João Sedoc | Juraj Juraska | Kaustubh Dhole | Khyathi Raghavi Chandu | Laura Perez Beltrachini | Leonardo F . R. Ribeiro | Lewis Tunstall | Li Zhang | Mahim Pushkarna | Mathias Creutz | Michael White | Mihir Sanjay Kale | Moussa Kamal Eddine | Nico Daheim | Nishant Subramani | Ondrej Dusek | Paul Pu Liang | Pawan Sasanka Ammanamanchi | Qi Zhu | Ratish Puduppully | Reno Kriz | Rifat Shahriyar | Ronald Cardenas | Saad Mahamood | Salomey Osei | Samuel Cahyawijaya | Sanja Štajner | Sebastien Montella | Shailza Jolly | Simon Mille | Tahmid Hasan | Tianhao Shen | Tosin Adewumi | Vikas Raunak | Vipul Raheja | Vitaly Nikolaev | Vivian Tsai | Yacine Jernite | Ying Xu | Yisi Sang | Yixin Liu | Yufang Hou
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. The compatibility, often facilitated through leaderboards, thus leads to outdated but standardized evaluation practices. We pose that the standardization is taking place in the wrong spot. Evaluation infrastructure should enable researchers to use the latest methods and what should be standardized instead is how to incorporate these new evaluation advances. We introduce GEMv2, the new version of the Generation, Evaluation, and Metrics Benchmark which uses a modular infrastructure for dataset, model, and metric developers to benefit from each other’s work. GEMv2 supports 40 documented datasets in 51 languages, ongoing online evaluation for all datasets, and our interactive tools make it easier to add new datasets to the living benchmark.

pdf bib
CoCoID: Learning Contrastive Representations and Compact Clusters for Semi-Supervised Intent Discovery
Qian Cao | Deyi Xiong | Qinlong Wang | Xia Peng
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track

Intent discovery is to mine new intents from user utterances, which are not present in the set of manually predefined intents. Previous approaches to intent discovery usually automatically cluster novel intents with prior knowledge from intent-labeled data in a semi-supervised way. In this paper, we focus on the discriminative user utterance representation learning and the compactness of the learned intent clusters. We propose a novel semi-supervised intent discovery framework CoCoID with two essential components: contrastive user utterance representation learning and intra-cluster knowledge distillation. The former attempts to detect similar and dissimilar intents from a minibatch-wise perspective. The latter regularizes the predictive distribution of the model over samples in a cluster-wise way. We conduct experiments on both real-life challenging datasets (i.e., CLINC and BANKING) that are curated to emulate the true environment of commercial/production systems and traditional datasets (i.e., StackOverflow and DBPedia) to evaluate the proposed CoCoID. Experiment results demonstrate that our model substantially outperforms state-of-the-art intent discovery models (12 baselines) by over 1.4 ACC and ARI points and 1.1 NMI points across the four datasets. Further analyses suggest that CoCoID is able to learn contrastive representations and compact clusters for intent discovery.

2021

pdf bib
AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation
Wuwei Huang | Dexin Wang | Deyi Xiong
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability
Kaiyu Huang | Junpeng Liu | Degen Huang | Deyi Xiong | Zhuang Liu | Jinsong Su
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Learning Hard Retrieval Decoder Attention for Transformers
Hongfei Xu | Qiuhui Liu | Josef van Genabith | Deyi Xiong
Findings of the Association for Computational Linguistics: EMNLP 2021

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by jointly attending to information from different representation subspaces at different positions. In this paper, we present an approach to learning a hard retrieval attention where an attention head only attends to one token in the sentence rather than all tokens. The matrix multiplication between attention probabilities and the value sequence in the standard scaled dot-product attention can thus be replaced by a simple and efficient retrieval operation. We show that our hard retrieval attention mechanism is 1.43 times faster in decoding, while preserving translation quality on a wide range of machine translation tasks when used in the decoder self- and cross-attention networks.

pdf bib
Secoco: Self-Correcting Encoding for Neural Machine Translation
Tao Wang | Chengqi Zhao | Mingxuan Wang | Lei Li | Hang Li | Deyi Xiong
Findings of the Association for Computational Linguistics: EMNLP 2021

This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with noisy input for robust neural machine translation by introducing self-correcting predictors. Different from previous robust approaches, Secoco enables NMT to explicitly correct noisy inputs and delete specific errors simultaneously with the translation decoding process. Secoco is able to achieve significant improvements over strong baselines on two real-world test sets and a benchmark WMT dataset with good interpretability. We will make our code and dataset publicly available soon.

pdf bib
Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data
Erguang Yang | Mingtong Liu | Deyi Xiong | Yujie Zhang | Yao Meng | Changjian Hu | Jinan Xu | Yufeng Chen
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Previous works on syntactically controlled paraphrase generation heavily rely on large-scale parallel paraphrase data that is not easily available for many languages and domains. In this paper, we take this research direction to the extreme and investigate whether it is possible to learn syntactically controlled paraphrase generation with nonparallel data. We propose a syntactically-informed unsupervised paraphrasing model based on conditional variational auto-encoder (VAE) which can generate texts in a specified syntactic structure. Particularly, we design a two-stage learning method to effectively train the model using non-parallel data. The conditional VAE is trained to reconstruct the input sentence according to the given input and its syntactic structure. Furthermore, to improve the syntactic controllability and semantic consistency of the pre-trained conditional VAE, we fine-tune it using syntax controlling and cycle reconstruction learning objectives, and employ Gumbel-Softmax to combine these new learning objectives. Experiment results demonstrate that the proposed model trained only on non-parallel data is capable of generating diverse paraphrases with specified syntactic structure. Additionally, we validate the effectiveness of our method for generating syntactically adversarial examples on the sentiment analysis task.

pdf bib
Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text Classification
Jiachen Tian | Shizhan Chen | Xiaowang Zhang | Zhiyong Feng | Deyi Xiong | Shaojuan Wu | Chunliu Dou
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Difficult samples of the minority class in imbalanced text classification are usually hard to be classified as they are embedded into an overlapping semantic region with the majority class. In this paper, we propose a Mutual Information constrained Semantically Oversampling framework (MISO) that can generate anchor instances to help the backbone network determine the re-embedding position of a non-overlapping representation for each difficult sample. MISO consists of (1) a semantic fusion module that learns entangled semantics among difficult and majority samples with an adaptive multi-head attention mechanism, (2) a mutual information loss that forces our model to learn new representations of entangled semantics in the non-overlapping region of the minority class, and (3) a coupled adversarial encoder-decoder that fine-tunes disentangled semantic representations to remain their correlations with the minority class, and then using these disentangled semantic representations to generate anchor instances for each difficult sample. Experiments on a variety of imbalanced text classification tasks demonstrate that anchor instances help classifiers achieve significant improvements over strong baselines.

pdf bib
Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context
Huibin Ge | Chenxi Sun | Deyi Xiong | Qun Liu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

This paper presents a Chinese dataset for evaluating pretrained language models on Word Prediction given Long-term Context (Chinese WPLC). We propose both automatic and manual selection strategies tailored to Chinese to guarantee that target words in passages collected from over 69K novels can only be predicted with long-term context beyond the scope of sentences containing the target words. Dataset analysis reveals that the types of target words range from common nouns to Chinese 4-character idioms. We also observe that linguistic relations between target words and long-range context exhibit diversity, including lexical match, synonym, summary and reasoning. Experiment results show that the Chinese pretrained language model PanGu-𝛼 is 45 points behind human in terms of top-1 word prediction accuracy, indicating that Chinese WPLC is a challenging dataset. The dataset is publicly available at https://git.openi.org.cn/PCL-Platform.Intelligence/Chinese_WPLC.

pdf bib
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers
Hongfei Xu | Josef van Genabith | Qiuhui Liu | Deyi Xiong
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Due to its effectiveness and performance, the Transformer translation model has attracted wide attention, most recently in terms of probing-based approaches. Previous work focuses on using or probing source linguistic features in the encoder. To date, the way word translation evolves in Transformer layers has not yet been investigated. Naively, one might assume that encoder layers capture source information while decoder layers translate. In this work, we show that this is not quite the case: translation already happens progressively in encoder layers and even in the input embeddings. More surprisingly, we find that some of the lower decoder layers do not actually do that much decoding. We show all of this in terms of a probing approach where we project representations of the layer analyzed to the final trained and frozen classifier level of the Transformer decoder to measure word translation accuracy. Our findings motivate and explain a Transformer configuration change: if translation already happens in the encoder layers, perhaps we can increase the number of encoder layers, while decreasing the number of decoder layers, boosting decoding speed, without loss in translation quality? Our experiments show that this is indeed the case: we can increase speed by up to a factor 2.3 with small gains in translation quality, while an 18-4 deep encoder configuration boosts translation quality by +1.42 BLEU (En-De) at a speed-up of 1.4.

pdf bib
Autocorrect in the Process of Translation — Multi-task Learning Improves Dialogue Machine Translation
Tao Wang | Chengqi Zhao | Mingxuan Wang | Lei Li | Deyi Xiong
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers

Automatic translation of dialogue texts is a much needed demand in many real life scenarios. However, the currently existing neural machine translation delivers unsatisfying results. In this paper, we conduct a deep analysis of a dialogue corpus and summarize three major issues on dialogue translation, including pronoun dropping (), punctuation dropping (), and typos (). In response to these challenges, we propose a joint learning method to identify omission and typo, and utilize context to translate dialogue utterances. To properly evaluate the performance, we propose a manually annotated dataset with 1,931 Chinese-English parallel utterances from 300 dialogues as a benchmark testbed for dialogue translation. Our experiments show that the proposed method improves translation quality by 3.2 BLEU over the baselines. It also elevates the recovery rate of omitted pronouns from 26.09% to 47.16%. We will publish the code and dataset publicly at https://xxx.xx.

pdf bib
Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation
Hongfei Xu | Qiuhui Liu | Josef van Genabith | Deyi Xiong | Meng Zhang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

One of the reasons Transformer translation models are popular is that self-attention networks for context modelling can be easily parallelized at sequence level. However, the computational complexity of a self-attention network is O(n2), increasing quadratically with sequence length. By contrast, the complexity of LSTM-based approaches is only O(n). In practice, however, LSTMs are much slower to train than self-attention networks as they cannot be parallelized at sequence level: to model context, the current LSTM state relies on the full LSTM computation of the preceding state. This has to be computed n times for a sequence of length n. The linear transformations involved in the LSTM gate and state computations are the major cost factors in this. To enable sequence-level parallelization of LSTMs, we approximate full LSTM context modelling by computing hidden states and gates with the current input and a simple bag-of-words representation of the preceding tokens context. This allows us to compute each input step efficiently in parallel, avoiding the formerly costly sequential linear transformations. We then connect the outputs of each parallel step with computationally cheap element-wise computations. We call this the Highly Parallelized LSTM. To further constrain the number of LSTM parameters, we compute several small HPLSTMs in parallel like multi-head attention in the Transformer. The experiments show that our MHPLSTM decoder achieves significant BLEU improvements, while being even slightly faster than the self-attention network in training, and much faster than the standard LSTM.

pdf bib
CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals
Yuqi Ren | Deyi Xiong
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Most previous studies integrate cognitive language processing signals (e.g., eye-tracking or EEG data) into neural models of natural language processing (NLP) just by directly concatenating word embeddings with cognitive features, ignoring the gap between the two modalities (i.e., textual vs. cognitive) and noise in cognitive features. In this paper, we propose a CogAlign approach to these issues, which learns to align textual neural representations to cognitive features. In CogAlign, we use a shared encoder equipped with a modality discriminator to alternatively encode textual and cognitive inputs to capture their differences and commonalities. Additionally, a text-aware attention mechanism is proposed to detect task-related information and to avoid using noise in cognitive features. Experimental results on three NLP tasks, namely named entity recognition, sentiment analysis and relation extraction, show that CogAlign achieves significant improvements with multiple cognitive features over state-of-the-art models on public datasets. Moreover, our model is able to transfer cognitive information to other datasets that do not have any cognitive processing signals.

pdf bib
TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models
Jie He | Bo Peng | Yi Liao | Qun Liu | Deyi Xiong
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

In order to deeply understand the capability of pretrained language models in text generation and conduct a diagnostic evaluation, we propose TGEA, an error-annotated dataset with multiple benchmark tasks for text generation from pretrained language models (PLMs). We use carefully selected prompt words to guide GPT-2 to generate candidate sentences, from which we select 47K for error annotation. Crowdsourced workers manually check each of these sentences and detect 12k erroneous sentences. We create an error taxonomy to cover 24 types of errors occurring in these erroneous sentences according to the nature of errors with respect to linguistics and knowledge (e.g., common sense). For each erroneous span in PLM-generated sentences, we also detect another span that is closely associated with it. Each error is hence manually labeled with comprehensive annotations, including the span of the error, the associated span, minimal correction to the error, the type of the error, and rationale behind the error. Apart from the fully annotated dataset, we also present a detailed description of the data collection procedure, statistics and analysis of the dataset. This is the first dataset with comprehensive annotations for PLM-generated texts, which facilitates the diagnostic evaluation of PLM-based text generation. Furthermore, we use TGEA as a benchmark dataset and propose a series of automatic diagnosis tasks, including error detection, error type classification, associated span detection, error rationale generation, to further promote future study on the automatic error detection and correction on texts generated by pretrained language models.

pdf bib
Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation
Hongfei Xu | Qiuhui Liu | Josef van Genabith | Deyi Xiong
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Neural machine translation has achieved great success in bilingual settings, as well as in multilingual settings. With the increase of the number of languages, multilingual systems tend to underperform their bilingual counterparts. Model capacity has been found crucial for massively multilingual NMT to support language pairs with varying typological characteristics. Previous work increases the modeling capacity by deepening or widening the Transformer. However, modeling cardinality based on aggregating a set of transformations with the same topology has been proven more effective than going deeper or wider when increasing capacity. In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality. Unlike previous work which feeds the same input to several transformations and merges their outputs into one, we present a Multi-Input-Multi-Output (MIMO) architecture that allows each transformation of the block to have its own input. We also present a task-aware attention mechanism to learn to selectively utilize individual transformations from a set of transformations for different translation directions. Our model surpasses previous work and establishes a new state-of-the-art on the large scale OPUS-100 corpus while being 1.31 times as fast.

pdf bib
An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter
Zhiyuan Zeng | Deyi Xiong
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

In this paper, we empirically investigate adversarial attack on NMT from two aspects: languages (the source vs. the target language) and positions (front vs. rear). For autoregressive NMT models that generate target words from left to right, we observe that adversarial attack on the source language is more effective than on the target language, and that attacking front positions of target sentences or positions of source sentences aligned to the front positions of corresponding target sentences is more effective than attacking other positions. We further exploit the attention distribution of the victim model to attack source sentences at positions that have a strong association with front target words. Experiment results demonstrate that our attention-based adversarial attack is more effective than adversarial attacks by sampling positions randomly or according to gradients.

2020

pdf bib
Proceedings of the Second International Workshop of Discourse Processing
Qun Liu | Deyi Xiong | Shili Ge | Xiaojun Zhang
Proceedings of the Second International Workshop of Discourse Processing

pdf bib
A Test Suite for Evaluating Discourse Phenomena in Document-level Neural Machine Translation
Xinyi Cai | Deyi Xiong
Proceedings of the Second International Workshop of Discourse Processing

The need to evaluate the ability of context-aware neural machine translation (NMT) models in dealing with specific discourse phenomena arises in document-level NMT. However, test sets that satisfy this need are rare. In this paper, we propose a test suite to evaluate three common discourse phenomena in English-Chinese translation: pronoun, discourse connective and ellipsis where discourse divergences lie across the two languages. The test suite contains 1,200 instances, 400 for each type of discourse phenomena. We perform both automatic and human evaluation with three state-of-the-art context-aware NMT models on the proposed test suite. Results suggest that our test suite can be used as a challenging benchmark test bed for evaluating document-level NMT. The test suite will be publicly available soon.

pdf bib
RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling
Jun Quan | Shian Zhang | Qian Cao | Zizhong Li | Deyi Xiong
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In order to alleviate the shortage of multi-domain data and to capture discourse phenomena for task-oriented dialogue modeling, we propose RiSAWOZ, a large-scale multi-domain Chinese Wizard-of-Oz dataset with Rich Semantic Annotations. RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues, with more than 150K utterances spanning over 12 domains, which is larger than all previous annotated H2H conversational datasets. Both single- and multi-domain dialogues are constructed, accounting for 65% and 35%, respectively. Each dialogue is labeled with comprehensive dialogue annotations, including dialogue goal in the form of natural language description, domain, dialogue states and acts at both the user and system side. In addition to traditional dialogue annotations, we especially provide linguistic annotations on discourse phenomena, e.g., ellipsis and coreference, in dialogues, which are useful for dialogue coreference and ellipsis resolution tasks. Apart from the fully annotated dataset, we also present a detailed description of the data collection procedure, statistics and analysis of the dataset. A series of benchmark models and results are reported, including natural language understanding (intent detection & slot filling), dialogue state tracking and dialogue context-to-text generation, as well as coreference and ellipsis resolution, which facilitate the baseline comparison for future research on this corpus.

pdf bib
TED-CDB: A Large-Scale Chinese Discourse Relation Dataset on TED Talks
Wanqiu Long | Bonnie Webber | Deyi Xiong
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

As different genres are known to differ in their communicative properties and as previously, for Chinese, discourse relations have only been annotated over news text, we have created the TED-CDB dataset. TED-CDB comprises a large set of TED talks in Chinese that have been manually annotated according to the goals and principles of Penn Discourse Treebank, but adapted to features that are not present in English. It serves as a unique Chinese corpus of spoken discourse. Benchmark experiments show that TED-CDB poses a challenge for state-of-the-art discourse relation classifiers, whose F1 performance on 4-way classification is 60%. This is a dramatic drop of 35% from performance on the news text in the Chinese Discourse Treebank. Transfer learning experiments have been carried out with the TED-CDB for both same-language cross-domain transfer and same-domain cross-language transfer. Both demonstrate that the TED-CDB can improve the performance of systems being developed for languages other than Chinese and would be helpful for insufficient or unbalanced data in other corpora. The dataset and our Chinese annotation guidelines will be made freely available.

pdf bib
Shallow Discourse Annotation for Chinese TED Talks
Wanqiu Long | Xinyi Cai | James Reid | Bonnie Webber | Deyi Xiong
Proceedings of the Twelfth Language Resources and Evaluation Conference

Text corpora annotated with language-related properties are an important resource for the development of Language Technology. The current work contributes a new resource for Chinese Language Technology and for Chinese-English translation, in the form of a set of TED talks (some originally given in English, some in Chinese) that have been annotated with discourse relations in the style of the Penn Discourse TreeBank, adapted to properties of Chinese text that are not present in English. The resource is currently unique in annotating discourse-level properties of planned spoken monologues rather than of written text. An inter-annotator agreement study demonstrates that the annotation scheme is able to achieve highly reliable results.

pdf bib
The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation
Jie He | Tao Wang | Deyi Xiong | Qun Liu
Findings of the Association for Computational Linguistics: EMNLP 2020

Does neural machine translation yield translations that are congenial with common sense? In this paper, we present a test suite to evaluate the commonsense reasoning capability of neural machine translation. The test suite consists of three test sets, covering lexical and contextless/contextual syntactic ambiguity that requires commonsense knowledge to resolve. We manually create 1,200 triples, each of which contain a source sentence and two contrastive translations, involving 7 different common sense types. Language models pretrained on large-scale corpora, such as BERT, GPT-2, achieve a commonsense reasoning accuracy of lower than 72% on target translations of this test suite. We conduct extensive experiments on the test suite to evaluate commonsense reasoning in neural machine translation and investigate factors that have impact on this capability. Our experiments and analyses demonstrate that neural machine translation performs poorly on commonsense reasoning of the three ambiguity types in terms of both reasoning accuracy ( 6 60.1%) and reasoning consistency (6 31%). We will release our test suite as a machine translation commonsense reasoning testbed to promote future work in this direction.

pdf bib
Learning Source Phrase Representations for Neural Machine Translation
Hongfei Xu | Josef van Genabith | Deyi Xiong | Qiuhui Liu | Jingyi Zhang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine Translation (NMT). Though intuitively the attentional network can connect distant words via shorter network paths than RNNs, empirical analysis demonstrates that it still has difficulty in fully capturing long-distance dependencies (Tang et al., 2018). Considering that modeling phrases instead of words has significantly improved the Statistical Machine Translation (SMT) approach through the use of larger translation blocks (“phrases”) and its reordering ability, modeling NMT at phrase level is an intuitive proposal to help the model capture long-distance relationships. In this paper, we first propose an attentive phrase representation generation mechanism which is able to generate phrase representations from corresponding token representations. In addition, we incorporate the generated phrase representations into the Transformer translation model to enhance its ability to capture long-distance relationships. In our experiments, we obtain significant improvements on the WMT 14 English-German and English-French tasks on top of the strong Transformer baseline, which shows the effectiveness of our approach. Our approach helps Transformer Base models perform at the level of Transformer Big models, and even significantly better for long sentences, but with substantially fewer parameters and training steps. The fact that phrase representations help even in the big setting further supports our conjecture that they make a valuable contribution to long-distance relations.

pdf bib
Lipschitz Constrained Parameter Initialization for Deep Transformers
Hongfei Xu | Qiuhui Liu | Josef van Genabith | Deyi Xiong | Jingyi Zhang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

The Transformer translation model employs residual connection and layer normalization to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. Previous research shows that even with residual connection and layer normalization, deep Transformers still have difficulty in training, and particularly Transformer models with more than 12 encoder/decoder layers fail to converge. In this paper, we first empirically demonstrate that a simple modification made in the official implementation, which changes the computation order of residual connection and layer normalization, can significantly ease the optimization of deep Transformers. We then compare the subtle differences in computation order in considerable detail, and present a parameter initialization method that leverages the Lipschitz constraint on the initialization of Transformer parameters that effectively ensures training convergence. In contrast to findings in previous research we further demonstrate that with Lipschitz parameter initialization, deep Transformers with the original computation order can converge, and obtain significant BLEU improvements with up to 24 layers. In contrast to previous research which focuses on deep encoders, our approach additionally enables Transformers to also benefit from deep decoders.

pdf bib
Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change
Hongfei Xu | Josef van Genabith | Deyi Xiong | Qiuhui Liu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

The choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on accelerating convergence and reducing the effects of the learning rate, comparatively few papers concentrate on the effect of batch size. In this paper, we analyze how increasing batch size affects gradient direction, and propose to evaluate the stability of gradients with their angle change. Based on our observations, the angle change of gradient direction first tends to stabilize (i.e. gradually decrease) while accumulating mini-batches, and then starts to fluctuate. We propose to automatically and dynamically determine batch sizes by accumulating gradients of mini-batches and performing an optimization step at just the time when the direction of gradients starts to fluctuate. To improve the efficiency of our approach for large models, we propose a sampling approach to select gradients of parameters sensitive to the batch size. Our approach dynamically determines proper and efficient batch sizes during training. In our experiments on the WMT 14 English to German and English to French tasks, our approach improves the Transformer with a fixed 25k batch size by +0.73 and +0.82 BLEU respectively.

pdf bib
Modeling Long Context for Task-Oriented Dialogue State Generation
Jun Quan | Deyi Xiong
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Based on the recently proposed transferable dialogue state generator (TRADE) that predicts dialogue states from utterance-concatenated dialogue context, we propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model as an auxiliary task for task-oriented dialogue state generation. By enabling the model to learn a better representation of the long dialogue context, our approaches attempt to solve the problem that the performance of the baseline significantly drops when the input dialogue context sequence is long. In our experiments, our proposed model achieves a 7.03% relative improvement over the baseline, establishing a new state-of-the-art joint goal accuracy of 52.04% on the MultiWOZ 2.0 dataset.

pdf bib
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer
Yufang Huang | Wentao Zhu | Deyi Xiong | Yiye Zhang | Changjian Hu | Feiyu Xu
Proceedings of the 28th International Conference on Computational Linguistics

Unsupervised text style transfer is full of challenges due to the lack of parallel data and difficulties in content preservation. In this paper, we propose a novel neural approach to unsupervised text style transfer which we refer to as Cycle-consistent Adversarial autoEncoders (CAE) trained from non-parallel data. CAE consists of three essential components: (1) LSTM autoencoders that encode a text in one style into its latent representation and decode an encoded representation into its original text or a transferred representation into a style-transferred text, (2) adversarial style transfer networks that use an adversarially trained generator to transform a latent representation in one style into a representation in another style, and (3) a cycle-consistent constraint that enhances the capacity of the adversarial style transfer networks in content preservation. The entire CAE with these three components can be trained end-to-end. Extensive experiments and in-depth analyses on two widely-used public datasets consistently validate the effectiveness of proposed CAE in both style transfer and content preservation against several strong baselines in terms of four automatic evaluation metrics and human evaluation.

pdf bib
A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning
Mingtong Liu | Erguang Yang | Deyi Xiong | Yujie Zhang | Yao Meng | Changjian Hu | Jinan Xu | Yufeng Chen
Proceedings of the 28th International Conference on Computational Linguistics

Paraphrase generation (PG) is of great importance to many downstream tasks in natural language processing. Diversity is an essential nature to PG for enhancing generalization capability and robustness of downstream applications. Recently, neural sequence-to-sequence (Seq2Seq) models have shown promising results in PG. However, traditional model training for PG focuses on optimizing model prediction against single reference and employs cross-entropy loss, which objective is unable to encourage model to generate diverse paraphrases. In this work, we present a novel approach with multi-objective learning to PG. We propose a learning-exploring method to generate sentences as learning objectives from the learned data distribution, and employ reinforcement learning to combine these new learning objectives for model training. We first design a sample-based algorithm to explore diverse sentences. Then we introduce several reward functions to evaluate the sampled sentences as learning signals in terms of expressive diversity and semantic fidelity, aiming to generate diverse and high-quality paraphrases. To effectively optimize model performance satisfying different evaluating aspects, we use a GradNorm-based algorithm that automatically balances these training objectives. Experiments and analyses on Quora and Twitter datasets demonstrate that our proposed method not only gains a significant increase in diversity but also improves generation quality over several state-of-the-art baselines.

pdf bib
Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling
Xu Cao | Deyi Xiong | Chongyang Shi | Chao Wang | Yao Meng | Changjian Hu
Proceedings of the 28th International Conference on Computational Linguistics

Joint intent detection and slot filling has recently achieved tremendous success in advancing the performance of utterance understanding. However, many joint models still suffer from the robustness problem, especially on noisy inputs or rare/unseen events. To address this issue, we propose a Joint Adversarial Training (JAT) model to improve the robustness of joint intent detection and slot filling, which consists of two parts: (1) automatically generating joint adversarial examples to attack the joint model, and (2) training the model to defend against the joint adversarial examples so as to robustify the model on small perturbations. As the generated joint adversarial examples have different impacts on the intent detection and slot filling loss, we further propose a Balanced Joint Adversarial Training (BJAT) model that applies a balance factor as a regularization term to the final loss function, which yields a stable training procedure. Extensive experiments and analyses on the lightweight models show that our proposed methods achieve significantly higher scores and substantially improve the robustness of both intent detection and slot filling. In addition, the combination of our BJAT with BERT-large achieves state-of-the-art results on two datasets.

2019

pdf bib
Towards Linear Time Neural Machine Translation with Capsule Networks
Mingxuan Wang | Jun Xie | Zhixing Tan | Jinsong Su | Deyi Xiong | Lei Li
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

In this study, we first investigate a novel capsule network with dynamic routing for linear time Neural Machine Translation (NMT), referred as CapsNMT. CapsNMT uses an aggregation mechanism to map the source sentence into a matrix with pre-determined size, and then applys a deep LSTM network to decode the target sequence from the source representation. Unlike the previous work (CITATION) to store the source sentence with a passive and bottom-up way, the dynamic routing policy encodes the source sentence with an iterative process to decide the credit attribution between nodes from lower and higher layers. CapsNMT has two core properties: it runs in time that is linear in the length of the sequences and provides a more flexible way to aggregate the part-whole information of the source sentence. On WMT14 English-German task and a larger WMT14 English-French task, CapsNMT achieves comparable results with the Transformer system. To the best of our knowledge, this is the first work that capsule networks have been empirically investigated for sequence to sequence problems.

pdf bib
Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation
Xin Tan | Longyin Zhang | Deyi Xiong | Guodong Zhou
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Document-level machine translation (MT) remains challenging due to the difficulty in efficiently using document context for translation. In this paper, we propose a hierarchical model to learn the global context for document-level neural machine translation (NMT). This is done through a sentence encoder to capture intra-sentence dependencies and a document encoder to model document-level inter-sentence consistency and coherence. With this hierarchical architecture, we feedback the extracted global document context to each word in a top-down fashion to distinguish different translations of a word according to its specific surrounding context. In addition, since large-scale in-domain document-level parallel corpora are usually unavailable, we use a two-step training strategy to take advantage of a large-scale corpus with out-of-domain parallel sentence pairs and a small-scale corpus with in-domain parallel document pairs to achieve the domain adaptability. Experimental results on several benchmark corpora show that our proposed model can significantly improve document-level translation performance over several strong NMT baselines.

pdf bib
BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels
Yimin Jing | Deyi Xiong | Zhen Yan
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

This paper presents BiPaR, a bilingual parallel novel-style machine reading comprehension (MRC) dataset, developed to support multilingual and cross-lingual reading comprehension. The biggest difference between BiPaR and existing reading comprehension datasets is that each triple (Passage, Question, Answer) in BiPaR is written parallelly in two languages. We collect 3,667 bilingual parallel paragraphs from Chinese and English novels, from which we construct 14,668 parallel question-answer pairs via crowdsourced workers following a strict quality control procedure. We analyze BiPaR in depth and find that BiPaR offers good diversification in prefixes of questions, answer types and relationships between questions and passages. We also observe that answering questions of novels requires reading comprehension skills of coreference resolution, multi-sentence reasoning, and understanding of implicit causality, etc. With BiPaR, we build monolingual, multilingual, and cross-lingual MRC baseline models. Even for the relatively simple monolingual MRC on this dataset, experiments show that a strong BERT baseline is over 30 points behind human in terms of both EM and F1 score, indicating that BiPaR provides a challenging testbed for monolingual, multilingual and cross-lingual MRC on novels. The dataset is available at https://multinlp.github.io/BiPaR/.

pdf bib
GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue
Jun Quan | Deyi Xiong | Bonnie Webber | Changjian Hu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Ellipsis and co-reference are common and ubiquitous especially in multi-turn dialogues. In this paper, we treat the resolution of ellipsis and co-reference in dialogue as a problem of generating omitted or referred expressions from the dialogue context. We therefore propose a unified end-to-end Generative Ellipsis and CO-reference Resolution model (GECOR) in the context of dialogue. The model can generate a new pragmatically complete user utterance by alternating the generation and copy mode for each user utterance. A multi-task learning framework is further proposed to integrate the GECOR into an end-to-end task-oriented dialogue. In order to train both the GECOR and the multi-task learning framework, we manually construct a new dataset on the basis of the public dataset CamRest676 with both ellipsis and co-reference annotation. On this dataset, intrinsic evaluations on the resolution of ellipsis and co-reference show that the GECOR model significantly outperforms the sequence-to-sequence (seq2seq) baseline model in terms of EM, BLEU and F1 while extrinsic evaluations on the downstream dialogue task demonstrate that our multi-task learning framework with GECOR achieves a higher success rate of task completion than TSCP, a state-of-the-art end-to-end task-oriented dialogue model.

pdf bib
Generating Highly Relevant Questions
Jiazuo Qiu | Deyi Xiong
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

The neural seq2seq based question generation (QG) is prone to generating generic and undiversified questions that are poorly relevant to the given passage and target answer. In this paper, we propose two methods to address the issue. (1) By a partial copy mechanism, we prioritize words that are morphologically close to words in the input passage when generating questions; (2) By a QA-based reranker, from the n-best list of question candidates, we select questions that are preferred by both the QA and QG model. Experiments and analyses demonstrate that the proposed two methods substantially improve the relevance of generated questions to passages and answers.

pdf bib
Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)
Andrei Popescu-Belis | Sharid Loáiciga | Christian Hardmeier | Deyi Xiong
Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)

2018

pdf bib
Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches
Shaohui Kuang | Deyi Xiong | Weihua Luo | Guodong Zhou
Proceedings of the 27th International Conference on Computational Linguistics

Sentences in a well-formed text are connected to each other via various links to form the cohesive structure of the text. Current neural machine translation (NMT) systems translate a text in a conventional sentence-by-sentence fashion, ignoring such cross-sentence links and dependencies. This may lead to generate an incoherent target text for a coherent source text. In order to handle this issue, we propose a cache-based approach to modeling coherence for neural machine translation by capturing contextual information either from recently translated sentences or the entire document. Particularly, we explore two types of caches: a dynamic cache, which stores words from the best translation hypotheses of preceding sentences, and a topic cache, which maintains a set of target-side topical words that are semantically related to the document to be translated. On this basis, we build a new layer to score target words in these two caches with a cache-based neural model. Here the estimated probabilities from the cache-based neural model are combined with NMT probabilities into the final word prediction probabilities via a gating mechanism. Finally, the proposed cache-based neural model is trained jointly with NMT system in an end-to-end manner. Experiments and analysis presented in this paper demonstrate that the proposed cache-based model achieves substantial improvements over several state-of-the-art SMT and NMT baselines.

pdf bib
Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model
Shaohui Kuang | Deyi Xiong
Proceedings of the 27th International Conference on Computational Linguistics

Neural machine translation (NMT) systems are usually trained on a large amount of bilingual sentence pairs and translate one sentence at a time, ignoring inter-sentence information. This may make the translation of a sentence ambiguous or even inconsistent with the translations of neighboring sentences. In order to handle this issue, we propose an inter-sentence gate model that uses the same encoder to encode two adjacent sentences and controls the amount of information flowing from the preceding sentence to the translation of the current sentence with an inter-sentence gate. In this way, our proposed model can capture the connection between sentences and fuse recency from neighboring sentences into neural machine translation. On several NIST Chinese-English translation tasks, our experiments demonstrate that the proposed inter-sentence gate model achieves substantial improvements over the baseline.

pdf bib
Neural Machine Translation with Decoding History Enhanced Attention
Mingxuan Wang | Jun Xie | Zhixing Tan | Jinsong Su | Deyi Xiong | Chao Bian
Proceedings of the 27th International Conference on Computational Linguistics

Neural machine translation with source-side attention have achieved remarkable performance. however, there has been little work exploring to attend to the target-side which can potentially enhance the memory capbility of NMT. We reformulate a Decoding History Enhanced Attention mechanism (DHEA) to render NMT model better at selecting both source-side and target-side information. DHA enables dynamic control of the ratios at which source and target contexts contribute to the generation of target words, offering a way to weakly induce structure relations among both source and target tokens. It also allows training errors to be directly back-propagated through short-cut connections and effectively alleviates the gradient vanishing problem. The empirical study on Chinese-English translation shows that our model with proper configuration can improve by 0:9 BLEU upon Transformer and the best reported results in the dataset. On WMT14 English-German task and a larger WMT14 English-French task, our model achieves comparable results with the state-of-the-art.

pdf bib
Sentence Weighting for Neural Machine Translation Domain Adaptation
Shiqi Zhang | Deyi Xiong
Proceedings of the 27th International Conference on Computational Linguistics

In this paper, we propose a new sentence weighting method for the domain adaptation of neural machine translation. We introduce a domain similarity metric to evaluate the relevance between a sentence and an available entire domain dataset. The similarity of each sentence to the target domain is calculated with various methods. The computed similarity is then integrated into the training objective to weight sentences. The adaptation results on both IWSLT Chinese-English TED task and a task with only synthetic training parallel data show that our sentence weighting method is able to achieve an significant improvement over strong baselines.

pdf bib
Encoding Gated Translation Memory into Neural Machine Translation
Qian Cao | Deyi Xiong
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Translation memories (TM) facilitate human translators to reuse existing repetitive translation fragments. In this paper, we propose a novel method to combine the strengths of both TM and neural machine translation (NMT) for high-quality translation. We treat the target translation of a TM match as an additional reference input and encode it into NMT with an extra encoder. A gating mechanism is further used to balance the impact of the TM match on the NMT decoder. Experiment results on the UN corpus demonstrate that when fuzzy matches are higher than 50%, the quality of NMT translation can be significantly improved by over 10 BLEU points.

pdf bib
Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks
Biao Zhang | Deyi Xiong | Jinsong Su | Qian Lin | Huiji Zhang
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

In this paper, we propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation. The recurrent units of ATR are heavily simplified to have the smallest number of weight matrices among units of all existing gated RNNs. With the simple addition and subtraction operation, we introduce a twin-gated mechanism to build input and forget gates which are highly correlated. Despite this simplification, the essential non-linearities and capability of modeling long-distance dependencies are preserved. Additionally, the proposed ATR is more transparent than LSTM/GRU due to the simplification. Forward self-attention can be easily established in ATR, which makes the proposed network interpretable. Experiments on WMT14 translation tasks demonstrate that ATR-based neural machine translation can yield competitive performance on English-German and English-French language pairs in terms of both translation quality and speed. Further experiments on NIST Chinese-English translation, natural language inference and Chinese word segmentation verify the generality and applicability of ATR on different natural language processing tasks.

pdf bib
Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings
Shaohui Kuang | Junhui Li | António Branco | Weihua Luo | Deyi Xiong
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations between source words and their possible target counterparts are not explicitly stored. Source and target words are at the two ends of a long information processing procedure, mediated by hidden states at both the source encoding and the target decoding phases. This makes it possible that a source word is incorrectly translated into a target word that is not any of its admissible equivalent counterparts in the target language. In this paper, we seek to somewhat shorten the distance between source and target words in that procedure, and thus strengthen their association, by means of a method we term bridging source and target word embeddings. We experiment with three strategies: (1) a source-side bridging model, where source word embeddings are moved one step closer to the output target sequence; (2) a target-side bridging model, which explores the more relevant source word embeddings for the prediction of the target sequence; and (3) a direct bridging model, which directly connects source and target word embeddings seeking to minimize errors in the translation of ones by the others. Experiments and analysis presented in this paper demonstrate that the proposed bridging models are able to significantly improve quality of both sentence translation, in general, and alignment and translation of individual source words with target words, in particular.

pdf bib
Accelerating Neural Transformer via an Average Attention Network
Biao Zhang | Deyi Xiong | Jinsong Su
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we propose an average attention network as an alternative to the self-attention network in the decoder of the neural Transformer. The average attention network consists of two layers, with an average layer that models dependencies on previous positions and a gating layer that is stacked over the average layer to enhance the expressiveness of the proposed attention network. We apply this network on the decoder part of the neural Transformer to replace the original target-side self-attention model. With masking tricks and dynamic programming, our model enables the neural Transformer to decode sentences over four times faster than its original version with almost no loss in training time and translation performance. We conduct a series of experiments on WMT17 translation tasks, where on 6 different language pairs, we obtain robust and consistent speed-ups in decoding.

2017

pdf bib
Modeling Source Syntax for Neural Machine Translation
Junhui Li | Deyi Xiong | Zhaopeng Tu | Muhua Zhu | Min Zhang | Guodong Zhou
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly incorporated into NMT effectively to provide further improvements. Specifically, we linearize parse trees of source sentences to obtain structural label sequences. On the basis, we propose three different sorts of encoders to incorporate source syntax into NMT: 1) Parallel RNN encoder that learns word and label annotation vectors parallelly; 2) Hierarchical RNN encoder that learns word and label annotation vectors in a two-level hierarchy; and 3) Mixed RNN encoder that stitchingly learns word and label annotation vectors over sequences where words and labels are mixed. Experimentation on Chinese-to-English translation demonstrates that all the three proposed syntactic encoders are able to improve translation accuracy. It is interesting to note that the simplest RNN encoder, i.e., Mixed RNN encoder yields the best performance with an significant improvement of 1.4 BLEU points. Moreover, an in-depth analysis from several perspectives is provided to reveal how source syntax benefits NMT.

pdf bib
Translating Phrases in Neural Machine Translation
Xing Wang | Zhaopeng Tu | Deyi Xiong | Min Zhang
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Phrases play an important role in natural language understanding and machine translation (Sag et al., 2002; Villavicencio et al., 2005). However, it is difficult to integrate them into current neural machine translation (NMT) which reads and generates sentences word by word. In this work, we propose a method to translate phrases in NMT by integrating a phrase memory storing target phrases from a phrase-based statistical machine translation (SMT) system into the encoder-decoder architecture of NMT. At each decoding step, the phrase memory is first re-written by the SMT model, which dynamically generates relevant target phrases with contextual information provided by the NMT model. Then the proposed model reads the phrase memory to make probability estimations for all phrases in the phrase memory. If phrase generation is carried on, the NMT decoder selects an appropriate phrase from the memory to perform phrase translation and updates its decoding state by consuming the words in the selected phrase. Otherwise, the NMT decoder generates a word from the vocabulary as the general NMT decoder does. Experiment results on the Chinese to English translation show that the proposed model achieves significant improvements over the baseline on various test sets.

2016

pdf bib
Proceedings of the 2nd Workshop on Semantics-Driven Machine Translation (SedMT 2016)
Deyi Xiong | Kevin Duh | Eneko Agirre | Nora Aranberri | Houfeng Wang
Proceedings of the 2nd Workshop on Semantics-Driven Machine Translation (SedMT 2016)

pdf bib
Book Reviews: Semantic Similarity from Natural Language and Ontology Analysis by Sébastien Harispe, Sylvie Ranwez, Stefan Janaqi, and Jacky Montmain
Deyi Xiong
Computational Linguistics, Volume 42, Issue 4 - December 2016

pdf bib
Variational Neural Discourse Relation Recognizer
Biao Zhang | Deyi Xiong | Jinsong Su | Qun Liu | Rongrong Ji | Hong Duan | Min Zhang
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Variational Neural Machine Translation
Biao Zhang | Deyi Xiong | Jinsong Su | Hong Duan | Min Zhang
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

pdf bib
Learning Event Expressions via Bilingual Structure Projection
Fangyuan Li | Ruihong Huang | Deyi Xiong | Min Zhang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Identifying events of a specific type is a challenging task as events in texts are described in numerous and diverse ways. Aiming to resolve high complexities of event descriptions, previous work (Huang and Riloff, 2013) proposes multi-faceted event recognition and a bootstrapping method to automatically acquire both event facet phrases and event expressions from unannotated texts. However, to ensure high quality of learned phrases, this method is constrained to only learn phrases that match certain syntactic structures. In this paper, we propose a bilingual structure projection algorithm that explores linguistic divergences between two languages (Chinese and English) and mines new phrases with new syntactic structures, which have been ignored in the previous work. Experiments show that our approach can successfully find novel event phrases and structures, e.g., phrases headed by nouns. Furthermore, the newly mined phrases are capable of recognizing additional event descriptions and increasing the recall of event recognition.

pdf bib
Improving Statistical Machine Translation with Selectional Preferences
Haiqing Tang | Deyi Xiong | Min Zhang | Zhengxian Gong
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Long-distance semantic dependencies are crucial for lexical choice in statistical machine translation. In this paper, we study semantic dependencies between verbs and their arguments by modeling selectional preferences in the context of machine translation. We incorporate preferences that verbs impose on subjects and objects into translation. In addition, bilingual selectional preferences between source-side verbs and target-side arguments are also investigated. Our experiments on Chinese-to-English translation tasks with large-scale training data demonstrate that statistical machine translation using verbal selectional preferences can achieve statistically significant improvements over a state-of-the-art baseline.

pdf bib
Bilingual Autoencoders with Global Descriptors for Modeling Parallel Sentences
Biao Zhang | Deyi Xiong | Jinsong Su | Hong Duan | Min Zhang
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Parallel sentence representations are important for bilingual and cross-lingual tasks in natural language processing. In this paper, we explore a bilingual autoencoder approach to model parallel sentences. We extract sentence-level global descriptors (e.g. min, max) from word embeddings, and construct two monolingual autoencoders over these descriptors on the source and target language. In order to tightly connect the two autoencoders with bilingual correspondences, we force them to share the same decoding parameters and minimize a corpus-level semantic distance between the two languages. Being optimized towards a joint objective function of reconstruction and semantic errors, our bilingual antoencoder is able to learn continuous-valued latent representations for parallel sentences. Experiments on both intrinsic and extrinsic evaluations on statistical machine translation tasks show that our autoencoder achieves substantial improvements over the baselines.

pdf bib
Convolution-Enhanced Bilingual Recursive Neural Network for Bilingual Semantic Modeling
Jinsong Su | Biao Zhang | Deyi Xiong | Ruochen Li | Jianmin Yin
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Estimating similarities at different levels of linguistic units, such as words, sub-phrases and phrases, is helpful for measuring semantic similarity of an entire bilingual phrase. In this paper, we propose a convolution-enhanced bilingual recursive neural network (ConvBRNN), which not only exploits word alignments to guide the generation of phrase structures but also integrates multiple-level information of the generated phrase structures into bilingual semantic modeling. In order to accurately learn the semantic hierarchy of a bilingual phrase, we develop a recursive neural network to constrain the learned bilingual phrase structures to be consistent with word alignments. Upon the generated source and target phrase structures, we stack a convolutional neural network to integrate vector representations of linguistic units on the structures into bilingual phrase embeddings. After that, we fully incorporate information of different linguistic units into a bilinear semantic similarity model. We introduce two max-margin losses to train the ConvBRNN model: one for the phrase structure inference and the other for the semantic similarity model. Experiments on NIST Chinese-English translation tasks demonstrate the high quality of the generated bilingual phrase structures with respect to word alignments and the effectiveness of learned semantic similarities on machine translation.

pdf bib
Improving Translation Selection with Supersenses
Haiqing Tang | Deyi Xiong | Oier Lopez de Lacalle | Eneko Agirre
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Selecting appropriate translations for source words with multiple meanings still remains a challenge for statistical machine translation (SMT). One reason for this is that most SMT systems are not good at detecting the proper sense for a polysemic word when it appears in different contexts. In this paper, we adopt a supersense tagging method to annotate source words with coarse-grained ontological concepts. In order to enable the system to choose an appropriate translation for a word or phrase according to the annotated supersense of the word or phrase, we propose two translation models with supersense knowledge: a maximum entropy based model and a supersense embedding model. The effectiveness of our proposed models is validated on a large-scale English-to-Spanish translation task. Results indicate that our method can significantly improve translation quality via correctly conveying the meaning of the source language to the target language.

2015

pdf bib
Graph-Based Collective Lexical Selection for Statistical Machine Translation
Jinsong Su | Deyi Xiong | Shujian Huang | Xianpei Han | Junfeng Yao
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Bilingual Correspondence Recursive Autoencoder for Statistical Machine Translation
Jinsong Su | Deyi Xiong | Biao Zhang | Yang Liu | Junfeng Yao | Min Zhang
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Learning Semantic Representations for Nonterminals in Hierarchical Phrase-Based Translation
Xing Wang | Deyi Xiong | Min Zhang
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Shallow Convolutional Neural Network for Implicit Discourse Relation Recognition
Biao Zhang | Jinsong Su | Deyi Xiong | Yaojie Lu | Hong Duan | Junfeng Yao
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
A Context-Aware Topic Model for Statistical Machine Translation
Jinsong Su | Deyi Xiong | Yang Liu | Xianpei Han | Hongyu Lin | Junfeng Yao | Min Zhang
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

pdf bib
Proceedings of the 1st Workshop on Semantics-Driven Statistical Machine Translation (S2MT 2015)
Deyi Xiong | Kevin Duh | Christian Hardmeier | Roberto Navigli
Proceedings of the 1st Workshop on Semantics-Driven Statistical Machine Translation (S2MT 2015)

pdf bib
Learning bilingual distributed phrase represenations for statistical machine translation
Chaochao Wang | Deyi Xiong | Min Zhang | Chunyu Kit
Proceedings of Machine Translation Summit XV: Papers

2014

pdf bib
A Sense-Based Translation Model for Statistical Machine Translation
Deyi Xiong | Min Zhang
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Semantics, Discourse and Statistical Machine Translation
Deyi Xiong | Min Zhang
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: Tutorials

pdf bib
Modeling Term Translation for Document-informed Machine Translation
Fandong Meng | Deyi Xiong | Wenbin Jiang | Qun Liu
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf bib
Max-Margin Synchronous Grammar Induction for Machine Translation
Xinyan Xiao | Deyi Xiong
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Lexical Chain Based Cohesion Models for Document-Level Statistical Machine Translation
Deyi Xiong | Yang Ding | Min Zhang | Chew Lim Tan
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

pdf bib
Bilingual Lexical Cohesion Trigger Model for Document-Level Machine Translation
Guosheng Ben | Deyi Xiong | Zhiyang Teng | Yajuan Lü | Qun Liu
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2012

pdf bib
Unsupervised Discriminative Induction of Synchronous Grammar for Machine Translation
Xinyan Xiao | Deyi Xiong | Yang Liu | Qun Liu | Shouxun Lin
Proceedings of COLING 2012

pdf bib
A Topic Similarity Model for Hierarchical Phrase-based Translation
Xinyan Xiao | Deyi Xiong | Min Zhang | Qun Liu | Shouxun Lin
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

pdf bib
Modeling the Translation of Predicate-Argument Structure for SMT
Deyi Xiong | Min Zhang | Haizhou Li
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2011

pdf bib
Enhancing Language Models in Statistical Machine Translation with Backward N-grams and Mutual Information Triggers
Deyi Xiong | Min Zhang | Haizhou Li
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Proceedings of the Fifth International Workshop On Cross Lingual Information Access
Asif Ekbal | Deyi Xiong
Proceedings of the Fifth International Workshop On Cross Lingual Information Access

2010

pdf bib
Linguistically Annotated Reordering: Evaluation and Analysis
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Computational Linguistics, Volume 36, Issue 3 - September 2010

pdf bib
Error Detection for Statistical Machine Translation Using Linguistic Features
Deyi Xiong | Min Zhang | Haizhou Li
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

pdf bib
I2R’s machine translation system for IWSLT 2010
Xiangyu Duan | Rafael Banchs | Jun Lang | Deyi Xiong | Aiti Aw | Min Zhang | Haizhou Li
Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign

pdf bib
Learning Translation Boundaries for Phrase-Based Decoding
Deyi Xiong | Min Zhang | Haizhou Li
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

2009

pdf bib
I2R’s machine translation system for IWSLT 2009
Xiangyu Duan | Deyi Xiong | Hui Zhang | Min Zhang | Haizhou Li
Proceedings of the 6th International Workshop on Spoken Language Translation: Evaluation Campaign

In this paper, we describe the system and approach used by the Institute for Infocomm Research (I2R) for the IWSLT 2009 spoken language translation evaluation campaign. Two kinds of machine translation systems are applied, namely, phrase-based machine translation system and syntax-based machine translation system. To test syntax-based machine translation system on spoken language translation, variational systems are explored. On top of both phrase-based and syntax-based single systems, we further use rescoring method to improve the individual system performance and use system combination method to combine the strengths of the different individual systems. Rescoring is applied on each single system output, and system combination is applied on all rescoring outputs. Finally, our system combination framework shows better performance in Chinese-English BTEC task.

pdf bib
A Syntax-Driven Bracketing Model for Phrase-Based Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP

pdf bib
Efficient Beam Thresholding for Statistical Machine Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of Machine Translation Summit XII: Posters

pdf bib
A Source Dependency Model for Statistical Machine Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of Machine Translation Summit XII: Posters

2008

pdf bib
Refinements in BTG-based Statistical Machine Translation
Deyi Xiong | Min Zhang | AiTi Aw | Haitao Mi | Qun Liu | Shouxun Lin
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I

pdf bib
I2R multi-pass machine translation system for IWSLT 2008.
Boxing Chen | Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign

In this paper, we describe the system and approach used by the Institute for Infocomm Research (I2R) for the IWSLT 2008 spoken language translation evaluation campaign. In the system, we integrate various decoding algorithms into a multi-pass translation framework. The multi-pass approach enables us to utilize various decoding algorithm and to explore much more hypotheses. This paper reports our design philosophy, overall architecture, each individual system and various system combination methods that we have explored. The performance on development and test sets are reported in detail in the paper. The system has shown competitive performance with respect to the BLEU and METEOR measures in Chinese-English Challenge and BTEC tasks.

pdf bib
A Linguistically Annotated Reordering Model for BTG-based Statistical Machine Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of ACL-08: HLT, Short Papers

pdf bib
Linguistically Annotated BTG for Statistical Machine Translation
Deyi Xiong | Min Zhang | Aiti Aw | Haizhou Li
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

2007

pdf bib
A Dependency Treelet String Correspondence Model for Statistical Machine Translation
Deyi Xiong | Qun Liu | Shouxun Lin
Proceedings of the Second Workshop on Statistical Machine Translation

pdf bib
The ICT statistical machine translation systems for IWSLT 2007
Zhongjun He | Haitao Mi | Yang Liu | Deyi Xiong | Weihua Luo | Yun Huang | Zhixiang Ren | Yajuan Lu | Qun Liu
Proceedings of the Fourth International Workshop on Spoken Language Translation

In this paper, we give an overview of the ICT statistical machine translation systems for the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2007. In this year’s evaluation, we participated in the Chinese-English transcript translation task, and developed three systems based on different techniques: a formally syntax-based system Bruin, an extended phrase-based system Confucius and a linguistically syntax-based system Lynx. We will describe the models of these three systems, and compare their performance in detail. We set Bruin as our primary system, which ranks 2 among the 15 primary results according to the official evaluation results.

2006

pdf bib
Maximum Entropy Based Phrase Reordering Model for Statistical Machine Translation
Deyi Xiong | Qun Liu | Shouxun Lin
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

2005

pdf bib
Parsing the Penn Chinese Treebank with Semantic Knowledge
Deyi Xiong | Shuanglong Li | Qun Liu | Shouxun Lin | Yueliang Qian
Second International Joint Conference on Natural Language Processing: Full Papers

2003

pdf bib
HHMM-based Chinese Lexical Analyzer ICTCLAS
Hua-Ping Zhang | Hong-Kui Yu | De-Yi Xiong | Qun Liu
Proceedings of the Second SIGHAN Workshop on Chinese Language Processing

Search
Co-authors