Linlin Li


2021

pdf bib
DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling
Baojun Wang | Zhao Zhang | Kun Xu | Guang-Yuan Hao | Yuyang Zhang | Lifeng Shang | Linlin Li | Xiao Chen | Xin Jiang | Qun Liu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Incorporating lexical knowledge into deep learning models has been proved to be very effective for sequence labeling tasks. However, previous works commonly have difficulty dealing with large-scale dynamic lexicons which often cause excessive matching noise and problems of frequent updates. In this paper, we propose DyLex, a plug-in lexicon incorporation approach for BERT based sequence labeling tasks. Instead of leveraging embeddings of words in the lexicon as in conventional methods, we adopt word-agnostic tag embeddings to avoid re-training the representation while updating the lexicon. Moreover, we employ an effective supervised lexical knowledge denoising method to smooth out matching noise. Finally, we introduce a col-wise attention based knowledge fusion mechanism to guarantee the pluggability of the proposed framework. Experiments on ten datasets of three tasks show that the proposed framework achieves new SOTA, even with very large scale lexicons.

2020

pdf bib
TinyBERT: Distilling BERT for Natural Language Understanding
Xiaoqi Jiao | Yichun Yin | Lifeng Shang | Xin Jiang | Xiao Chen | Linlin Li | Fang Wang | Qun Liu
Findings of the Association for Computational Linguistics: EMNLP 2020

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently execute them on resource-restricted devices. To accelerate inference and reduce model size while maintaining accuracy, we first propose a novel Transformer distillation method that is specially designed for knowledge distillation (KD) of the Transformer-based models. By leveraging this new KD method, the plenty of knowledge encoded in a large “teacher” BERT can be effectively transferred to a small “student” TinyBERT. Then, we introduce a new two-stage learning framework for TinyBERT, which performs Transformer distillation at both the pre-training and task-specific learning stages. This framework ensures that TinyBERT can capture the general-domain as well as the task-specific knowledge in BERT. TinyBERT4 with 4 layers is empirically effective and achieves more than 96.8% the performance of its teacher BERT-Base on GLUE benchmark, while being 7.5x smaller and 9.4x faster on inference. TinyBERT4 is also significantly better than 4-layer state-of-the-art baselines on BERT distillation, with only ~28% parameters and ~31% inference time of them. Moreover, TinyBERT6 with 6 layers performs on-par with its teacher BERT-Base.

2019

pdf bib
A Neural Multi-digraph Model for Chinese NER with Gazetteers
Ruixue Ding | Pengjun Xie | Xiaoyan Zhang | Wei Lu | Linlin Li | Luo Si
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Gazetteers were shown to be useful resources for named entity recognition (NER). Many existing approaches to incorporating gazetteers into machine learning based NER systems rely on manually defined selection strategies or handcrafted templates, which may not always lead to optimal effectiveness, especially when multiple gazetteers are involved. This is especially the case for the task of Chinese NER, where the words are not naturally tokenized, leading to additional ambiguities. To automatically learn how to incorporate multiple gazetteers into an NER system, we propose a novel approach based on graph neural networks with a multi-digraph structure that captures the information that the gazetteers offer. Experiments on various datasets show that our model is effective in incorporating rich gazetteer information while resolving ambiguities, outperforming previous approaches.

pdf bib
DM_NLP at SemEval-2018 Task 12: A Pipeline System for Toponym Resolution
Xiaobin Wang | Chunping Ma | Huafei Zheng | Chu Liu | Pengjun Xie | Linlin Li | Luo Si
Proceedings of the 13th International Workshop on Semantic Evaluation

This paper describes DM-NLP’s system for toponym resolution task at Semeval 2019. Our system was developed for toponym detection, disambiguation and end-to-end resolution which is a pipeline of the former two. For toponym detection, we utilized the state-of-the-art sequence labeling model, namely, BiLSTM-CRF model as backbone. A lot of strategies are adopted for further improvement, such as pre-training, model ensemble, model averaging and data augment. For toponym disambiguation, we adopted the widely used searching and ranking framework. For ranking, we proposed several effective features for measuring the consistency between the detected toponym and toponyms in GeoNames. Eventually, our system achieved the best performance among all the submitted results in each sub task.

pdf bib
Better Modeling of Incomplete Annotations for Named Entity Recognition
Zhanming Jie | Pengjun Xie | Wei Lu | Ruixue Ding | Linlin Li
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Supervised approaches to named entity recognition (NER) are largely developed based on the assumption that the training data is fully annotated with named entity information. However, in practice, annotated data can often be imperfect with one typical issue being the training data may contain incomplete annotations. We highlight several pitfalls associated with learning under such a setup in the context of NER and identify limitations associated with existing approaches, proposing a novel yet easy-to-implement approach for recognizing named entities with incomplete data annotations. We demonstrate the effectiveness of our approach through extensive experiments.

pdf bib
Neural Chinese Address Parsing
Hao Li | Wei Lu | Pengjun Xie | Linlin Li
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

This paper introduces a new task – Chinese address parsing – the task of mapping Chinese addresses into semantically meaningful chunks. While it is possible to model this problem using a conventional sequence labelling approach, our observation is that there exist complex dependencies between labels that cannot be readily captured by a simple linear-chain structure. We investigate neural structured prediction models with latent variables to capture such rich structural information within Chinese addresses. We create and publicly release a new dataset consisting of 15K Chinese addresses, and conduct extensive experiments on the dataset to investigate the model effectiveness and robustness. We release our code and data at http://statnlp.org/research/sp.

2018

pdf bib
A Hybrid System for Chinese Grammatical Error Diagnosis and Correction
Chen Li | Junpei Zhou | Zuyi Bao | Hengyou Liu | Guangwei Xu | Linlin Li
Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications

This paper introduces the DM_NLP team’s system for NLPTEA 2018 shared task of Chinese Grammatical Error Diagnosis (CGED), which can be used to detect and correct grammatical errors in texts written by Chinese as a Foreign Language (CFL) learners. This task aims at not only detecting four types of grammatical errors including redundant words (R), missing words (M), bad word selection (S) and disordered words (W), but also recommending corrections for errors of M and S types. We proposed a hybrid system including four models for this task with two stages: the detection stage and the correction stage. In the detection stage, we first used a BiLSTM-CRF model to tag potential errors by sequence labeling, along with some handcraft features. Then we designed three Grammatical Error Correction (GEC) models to generate corrections, which could help to tune the detection result. In the correction stage, candidates were generated by the three GEC models and then merged to output the final corrections for M and S types. Our system reached the highest precision in the correction subtask, which was the most challenging part of this shared task, and got top 3 on F1 scores for position detection of errors.

pdf bib
DM_NLP at SemEval-2018 Task 8: neural sequence labeling with linguistic features
Chunping Ma | Huafei Zheng | Pengjun Xie | Chen Li | Linlin Li | Luo Si
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper describes our submissions for SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using NLP. The DM_NLP participated in two subtasks: SubTask 1 classifies if a sentence is useful for inferring malware actions and capabilities, and SubTask 2 predicts token labels (“Action”, “Entity”, “Modifier” and “Others”) for a given malware-related sentence. Since we leverage results of Subtask 2 directly to infer the result of Subtask 1, the paper focus on the system solving Subtask 2. By taking Subtask 2 as a sequence labeling task, our system relies on a recurrent neural network named BiLSTM-CNN-CRF with rich linguistic features, such as POS tags, dependency parsing labels, chunking labels, NER labels, Brown clustering. Our system achieved the highest F1 score in both token level and phrase level.

pdf bib
NLP_HZ at SemEval-2018 Task 9: a Nearest Neighbor Approach
Wei Qiu | Mosha Chen | Linlin Li | Luo Si
Proceedings of the 12th International Workshop on Semantic Evaluation

Hypernym discovery aims to discover the hypernym word sets given a hyponym word and proper corpus. This paper proposes a simple but effective method for the discovery of hypernym sets based on word embedding, which can be used to measure the contextual similarities between words. Given a test hyponym word, we get its hypernym lists by computing the similarities between the hyponym word and words in the training data, and fill the test word’s hypernym lists with the hypernym list in the training set of the nearest similarity distance to the test word. In SemEval 2018 task9, our results, achieve 1st on Spanish, 2nd on Italian, 6th on English in the metric of MAP.

pdf bib
A Unified Syntax-aware Framework for Semantic Role Labeling
Zuchao Li | Shexia He | Jiaxun Cai | Zhuosheng Zhang | Hai Zhao | Gongshen Liu | Linlin Li | Luo Si
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Semantic role labeling (SRL) aims to recognize the predicate-argument structure of a sentence. Syntactic information has been paid a great attention over the role of enhancing SRL. However, the latest advance shows that syntax would not be so important for SRL with the emerging much smaller gap between syntax-aware and syntax-agnostic SRL. To comprehensively explore the role of syntax for SRL task, we extend existing models and propose a unified framework to investigate more effective and more diverse ways of incorporating syntax into sequential neural networks. Exploring the effect of syntactic input quality on SRL performance, we confirm that high-quality syntactic parse could still effectively enhance syntactically-driven SRL. Using empirically optimized integration strategy, we even enlarge the gap between syntax-aware and syntax-agnostic SRL. Our framework achieves state-of-the-art results on CoNLL-2009 benchmarks both for English and Chinese, substantially outperforming all previous models.

2017

pdf bib
Alibaba at IJCNLP-2017 Task 1: Embedding Grammatical Features into LSTMs for Chinese Grammatical Error Diagnosis Task
Yi Yang | Pengjun Xie | Jun Tao | Guangwei Xu | Linlin Li | Luo Si
Proceedings of the IJCNLP 2017, Shared Tasks

This paper introduces Alibaba NLP team system on IJCNLP 2017 shared task No. 1 Chinese Grammatical Error Diagnosis (CGED). The task is to diagnose four types of grammatical errors which are redundant words (R), missing words (M), bad word selection (S) and disordered words (W). We treat the task as a sequence tagging problem and design some handcraft features to solve it. Our system is mainly based on the LSTM-CRF model and 3 ensemble strategies are applied to improve the performance. At the identification level and the position level our system gets the highest F1 scores. At the position level, which is the most difficult level, we perform best on all metrics.

2014

pdf bib
Improved Estimation of Entropy for Evaluation of Word Sense Induction
Linlin Li | Ivan Titov | Caroline Sporleder
Computational Linguistics, Volume 40, Issue 3 - September 2014

2010

pdf bib
Idioms in Context: The IDIX Corpus
Caroline Sporleder | Linlin Li | Philip Gorinski | Xaver Koch
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)

Idioms and other figuratively used expressions pose considerable problems to natural language processing applications because they are very frequent and often behave idiosyncratically. Consequently, there has been much research on the automatic detection and extraction of idiomatic expressions. Most studies focus on type-based idiom detection, i.e., distinguishing whether a given expression can (potentially) be used idiomatically. However, many expressions such as ""break the ice"" can have both literal and non-literal readings and need to be disambiguated in a given context (token-based detection). So far relatively few approaches have attempted context-based idiom detection. One reason for this may be that few annotated resources are available that disambiguate expressions in context. With the IDIX corpus, we aim to address this. IDIX is available as an add-on to the BNC and disambiguates different usages of a subset of idioms. We believe that this resource will be useful both for linguistic and computational linguistic studies.

pdf bib
Topic Models for Word Sense Disambiguation and Token-Based Idiom Detection
Linlin Li | Benjamin Roth | Caroline Sporleder
Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

pdf bib
Using Gaussian Mixture Models to Detect Figurative Language in Context
Linlin Li | Caroline Sporleder
Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics

pdf bib
Linguistic Cues for Distinguishing Literal and Non-Literal Usages
Linlin Li | Caroline Sporleder
Coling 2010: Posters

2009

pdf bib
Classifier Combination for Contextual Idiom Detection Without Labelled Data
Linlin Li | Caroline Sporleder
Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing

pdf bib
A Cohesion Graph Based Approach for Unsupervised Recognition of Literal and Non-literal Use of Multiword Expressions
Linlin Li | Caroline Sporleder
Proceedings of the 2009 Workshop on Graph-based Methods for Natural Language Processing (TextGraphs-4)

pdf bib
Unsupervised Recognition of Literal and Non-Literal Use of Idiomatic Expressions
Caroline Sporleder | Linlin Li
Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009)