Recently, with the chain of thought (CoT) prompting, large language models (LLMs), e.g., GPT-3, have shown strong reasoning ability in several natural language processing tasks such as arithmetic, commonsense, and logical reasoning. However, LLMs with CoT require multi-step prompting and multi-token prediction, which is highly sensitive to individual mistakes and vulnerable to error accumulation. The above issues make the LLMs need the ability to verify the answers. In fact, after inferring conclusions in some thinking decision tasks, people often check them by re-verifying steps to avoid some mistakes. In this paper, we propose and prove that LLMs also have similar self-verification abilities. We take the conclusion obtained by CoT as one of the conditions for solving the original problem. By performing a backward verification of the answers that LLM deduced for itself, we can obtain interpretable answer validation scores to select the candidate answer with the highest score. Experimental results demonstrate that the proposed method can improve the reasoning performance on various arithmetic, commonsense, and logical reasoning datasets. Our code is publicly available at: https://github.com/WENGSYX/Self-Verification.

This paper present the results of the First International Ancient Chinese Transalation Bakeoff (EvaHan), which is a shared task of the Ancient Language Translation Workshop (ALT2023) and a co-located event of the 19th Edition of the Machine Translation Summit 2023 (MTS 2023). We described the motivation for having an international shared contest, as well as the datasets and tracks. The contest consists of two modalities, closed and open. In the closed modality, the participants are only allowed to use the training data, the partic-ipating teams achieved the highest BLEU scores of 27.3315 and 1.1102 in the tasks of translating Ancient Chinese to Modern Chinese and translating Ancient Chinese to English, respectively. In the open mode, contestants can only use any available data and models. The participating teams achieved the highest BLEU scores of 29.6832 and 6.5493 in the ancient Chinese to modern and ancient Chinese to English tasks, respectively.

“动物词承载了大量人类社会认知映射,不同民族对于同一个词的认知有所异同。通过隐喻研究动物词认知差异是近年来十分流行的趋势,反映人们对词语认知印象的认知属性就是一个简捷的切入口。本文选择《中华传统文化名词认知属性库》中的54种动物,借助中英文认知属性数据库,对比分析英汉语言中的认知属性差异。文章发现动物词的英汉认知属性之间有明显差异,且差异更多表现在主观属性上,并发现了中英文中动物词认知属性的整体异同。”

“差比句是用来表达两个或多个事物之间的相似或不同之处的句子结构,常用句式为“X比Y+比较结果”。差比句存在多种结构变体且大量存在省略现象,造成汉语语法研究和自然语言处理任务困难,因此实现差比句结构的识别和对其缺省结构进行补全非常有意义。本文采用序列化标注方法构建了一个差比句语料库,提出了一个能够融合字与词信息的LatticeBERT-BILSTM-CRF模型来对差比句结构自动识别,并且能对缺省单位进行自动补全,实验结果验证了方法的有效性。”

“为辅助中小学教材及读本中唐诗的选取,本文基于对《唐诗三百首》分词、词性、典故标记的深加工语料库,据诗句可读性创新性地构建了分级标准,共分4层,共计8项可量化指标:字层(通假字)、词层(双字词)、句层(特殊句式、标题长度、诗句长度)、艺术层(典故、其他修辞、描写手法)。据以上8项指标对语料库中313首诗评分,建立基于量化特征的向量空间模型,以K-means聚类算法将诗歌聚类以对应小学、初中和高中3个学段的唐诗学习。”

“汉语被动句是一种重要的语言现象。本文采用BIO结合索引的标注方法,对被动句中的被动结构进行了细粒度标注,提出了一种基于BERT-wwm-ext预训练模型和双仿射注意力机制的CRF序列标注模型,实现对汉语被动句中内部结构的自动解析,F1值达到97.31%。本文提出的模型具有良好的泛化性,实验证明,利用本文模型的被动结构解析结果对CAMR图后处理,能有效提高CAMR被动句解析任务的性能。”

“Abstract Meaning Representation has emerged as a prominent area of research in sentence-levelsemantic parsing within the field of natural language processing in recent years. Substantialprogress has been made in various NLP subtasks through the application of AMR. This paperpresents the third Chinese Abstract Meaning Representation Parsing Evaluation, held as part ofthe Technical Evaluation Task Workshop at the 22nd Chinese Computational Linguistics Confer-ence. The evaluation was specifically tailored for the Chinese and utilized the Align-smatch met-ric as the standard evaluation criterion. Building upon high-quality semantic annotation schemesand annotated corpora, this evaluation introduced a new test set comprising interrogative sen-tences for comprehensive evaluation. The results of the evaluation, as measured by the F-score,indicate notable performance achievements. The top-performing team attained a score of 0.8137in the closed test and 0.8261 in the open test, respectively, using the Align-smatch metric. No-tably, the leading result surpassed the SOTA performance at CoNLL 2020 by 3.64 percentagepoints when evaluated using the MRP metric. Further analysis revealed that this significantprogress primarily stemmed from improved relation prediction between concepts. However, thechallenge of effectively utilizing semantic relation alignments remains an area that requires fur-ther enhancement.”

Commentary of Gongyang, Commentary of Guliang, and Commentary of Zuo are collectively called the Three Commentaries on the Spring and Autumn Annals, which are the supplement and interpretation of the content of Spring and Autumn Annals with value in historical and literary research. In traditional research paradigms, scholars often explored the differences between the Three Commentaries within the details in contexts. Starting from the view of computational humanities, this paper examines the differences in the language style of the Three Commentaries through the representation of language, which takes the methods of deep learning. Specifically, this study vectorizes the context at word and sentence levels. It maps them into the same plane to find the differences between the use of words and sentences in the Three Commentaries. The results show that the Commentary of Gongyang and the Commentary of Guliang are relatively similar, while the Commentary of Zuo is significantly different. This paper verifies the feasibility of deep learning methods in stylistics study under computational humanities. It provides a valuable perspective for studying the Three Commentaries on the Spring and Autumn Annals.

The digitization of ancient books necessitates the implementation of automatic word segmentation and part-of-speech tagging. However, the existing research on this topic encounters pressing issues, including suboptimal efficiency and precision, which require immediate resolution. This study employs a methodology that combines word segmentation and part-of-speech tagging. It establishes a correlation between fonts and radicals, trains the Radical2Vec radical vector representation model, and integrates it with the SikuRoBERTa word vector representation model. Finally, it connects the BiLSTM-CRF neural network.The study investigates the combination of word segmentation and part-of-speech tagging through an experimental approach using a specific data set. In the evaluation dataset, the F1 score for word segmentation is 95.75%, indicating a high level of accuracy. Similarly, the F1 score for part-of-speech tagging is 91.65%, suggesting a satisfactory performance in this task. This model enhances the efficiency and precision of the processing of ancient books, thereby facilitating the advancement of digitization efforts for ancient books and ensuring the preservation and advancement of ancient book heritage.

Abstract Meaning Representation is a sentence-level meaning representation, which abstracts the meaning of sentences into a rooted acyclic directed graph. With the continuous expansion of Chinese AMR corpus, more and more scholars have developed parsing systems to automatically parse sentences into Chinese AMR. However, the current parsers can’t deal with concept alignment and relation alignment, let alone the evaluation methods for AMR parsing. Therefore, to make up for the vacancy of Chinese AMR parsing evaluation methods, based on AMR evaluation metric smatch, we have improved the algorithm of generating triples so that to make it compatible with concept alignment and relation alignment. Finally, we obtain a new integrity metric align-smatch for paring evaluation. A comparative research then was conducted on 20 manually annotated AMR and gold AMR, with the result that align-smatch works well in alignments and more robust in evaluating arcs. We also put forward some fine-grained metric for evaluating concept alignment, relation alignment and implicit concepts, in order to further measure parsers’ performance in subtasks.

A recent success in semantic dependency parsing shows that graph neural networks can make significant accuracy improvements, owing to its powerful ability in learning expressive graph representations. However, this work learns graph representations based on a static graph constructed by an existing parser, suffering from two drawbacks: (1) the static graph might be error-prone (e.g., noisy or incomplete), and (2) graph construction stage and graph representation learning stage are disjoint, the errors introduced in the graph construction stage cannot be corrected and might be accumulated to later stages. To address these two drawbacks, we propose a dynamic graph learning framework and apply it to semantic dependency parsing, for jointly learning graph structure and graph representations. Experimental results show that our parser outperforms the previous parsers on the SemEval-2015 Task 18 dataset in three languages (English, Chinese, and Czech).

Emotion is the essential attribute of human beings. Perceiving and understanding emotions in a human-like manner is the most central part of developing emotional intelligence. This paper describes the contribution of the LingJing team’s method to the Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA) 2022 shared task on Emotion Classification. The participants are required to predict seven emotions from empathic responses to news or stories that caused harm to individuals, groups, or others. This paper describes the continual pre-training method for the masked language model (MLM) to enhance the DeBERTa pre-trained language model. Several training strategies are designed to further improve the final downstream performance including the data augmentation with the supervised transfer, child-tuning training, and the late fusion method. Extensive experiments on the emotional classification dataset show that the proposed method outperforms other state-of-the-art methods, demonstrating our method’s effectiveness. Moreover, our submission ranked Top-1 with all metrics in the evaluation phase for the Emotion Classification task.

This paper describes the LingJing team’s method to the Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA) 2022 shared task on Personality Prediction (PER) and Reactivity Index Prediction (IRI). In this paper, we adopt the prompt-based method with the pre-trained language model to accomplish these tasks. Specifically, the prompt is designed to provide knowledge of the extra personalized information for enhancing the pre-trained model. Data augmentation and model ensemble are adopted for obtaining better results. Extensive experiments are performed, which shows the effectiveness of the proposed method. On the final submission, our system achieves a Pearson Correlation Coefficient of 0.2301 and 0.2546 on Track 3 and Track 4 respectively. We ranked 1-st on both sub-tasks.

Visual Dialogue (VD) task has recently received increasing attention in AI research. Visual Dialog aims to generate multi-round, interactive responses based on the dialog history and image content. Existing textual dialogue models cannot fully understand visual information, resulting in a lack of scene features when communicating with humans continuously. Therefore, how to efficiently fuse multimodal data features remains to be a challenge. In this work, we propose a knowledge transfer method with visual prompt (VPTG) fusing multi-modal data, which is a flexible module that can utilize the text-only seq2seq model to handle visual dialogue tasks. The VPTG conducts text-image co-learning and multi-modal information fusion with visual prompts and visual knowledge distillation. Specifically, we construct visual prompts from visual representations and then induce sequence-to-sequence(seq2seq) models to fuse visual information and textual contexts by visual-text patterns. And we also realize visual knowledge transfer through distillation between two different models’ text representations, so that the seq2seq model can actively learn visual semantic representations. Extensive experiments on the multi-modal dialogue understanding and generation (MDUG) datasets show the proposed VPTG outperforms other single-modal methods, which demonstrate the effectiveness of visual prompt and visual knowledge transfer.

“汉语中的被动句根据有无被动标记词可分为有标记被动句和无标记被动句。由于其形态构成复杂多样,给自然语言理解带来很大困难,因此实现汉语被动句的自动识别对自然语言处理下游任务具有重要意义。本文构建了一个被动句语料库,提出了一个融合词性和动词论元框架信息的PC-BERT-CNN模型,对汉语被动句进行自动识别。实验结果表明,本文提出的模型能够准确地识别汉语被动句,其中有标记被动句识别F1值达到98.77%,无标记被动句识别F1值达到96.72%。”

Question Answering (QA) is a Natural Language Processing (NLP) task that can measure language and semantics understanding ability, it requires a system not only to retrieve relevant documents from a large number of articles but also to answer corresponding questions according to documents. However, various language styles and sources of human questions and evidence documents form the different embedding semantic spaces, which may bring some errors to the downstream QA task. To alleviate these problems, we propose a framework for enhancing downstream evidence retrieval by generating evidence, aiming at improving the performance of response generation. Specifically, we take the pre-training language model as a knowledge base, storing documents’ information and knowledge into model parameters. With the Child-Tuning approach being designed, the knowledge storage and evidence generation avoid catastrophic forgetting for response generation. Extensive experiments carried out on the multi-documents dataset show that the proposed method can improve the final performance, which demonstrates the effectiveness of the proposed framework.

This paper introduces the approach of VPAI_Lab team’s experiments on BioNLP 2022 shared task 1 Medical Video Classification (MedVidCL). Given an input video, the MedVidCL task aims to correctly classify it into one of three following categories: Medical Instructional, Medical Non-instructional, and Non-medical. Inspired by its dataset construction process, we divide the classification process into two stages. The first stage is to classify videos into medical videos and non-medical videos. In the second stage, for those samples classified as medical videos, we further classify them into instructional videos and non-instructional videos. In addition, we also propose the cross-modal fusion method to solve the video classification, such as fusing the text features (question and subtitles) from the pre-training language models and visual features from image frames. Specifically, we use textual information to concatenate and query the visual information for obtaining better feature representation. Extensive experiments show that the proposed method significantly outperforms the official baseline method by 15.4% in the F1 score, which shows its effectiveness. Finally, the online results show that our method ranks the Top-1 on the online unseen test set. All the experimental codes are open-sourced at https://github.com/Lireanstar/MedVidCL.

This paper introduces the approach of Team LingJing’s experiments on SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings (CODWOE). This task aims at comparing two types of semantic descriptions and including two sub-tasks: the definition modeling and reverse dictionary track. Our team focuses on the reverse dictionary track and adopts the multi-task self-supervised pre-training for multilingual reverse dictionaries. Specifically, the randomly initialized mDeBERTa-base model is used to perform multi-task pre-training on the multilingual training datasets. The pre-training step is divided into two stages, namely the MLM pre-training stage and the contrastive pre-training stage. The experimental results show that the proposed method has achieved good performance in the reverse dictionary track, where we rank the 1-st in the Sgns targets of the EN and RU languages. All the experimental codes are open-sourced at https://github.com/WENGSYX/Semeval.

This paper presents the results and main findings of our system on SemEval-2022 Task 3 Presupposed Taxonomies: Evaluating Neural Network Semantics (PreTENS). This task aims at semantic competence with specific attention on the evaluation of language models, which is a task with respect to the recognition of appropriate taxonomic relations between two nominal arguments. Two sub-tasks including binary classification and regression are designed for the evaluation. For the classification sub-task, we adopt the DeBERTa-v3 pre-trained model for fine-tuning datasets of different languages. Due to the small size of the training datasets of the regression sub-task, we transfer the knowledge of classification model (i.e., model parameters) to the regression task. The experimental results show that the proposed method achieves the best results on both sub-tasks. Meanwhile, we also report negative results of multiple training strategies for further discussion. All the experimental codes are open-sourced at https://github.com/WENGSYX/Semeval.

This paper presents the results of the First Ancient Chinese Word Segmentation and POS Tagging Bakeoff (EvaHan), which was held at the Second Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) 2022, in the context of the 13th Edition of the Language Resources and Evaluation Conference (LREC 2022). We give the motivation for having an international shared contest, as well as the data and tracks. The contest is consisted of two modalities, closed and open. In the closed modality, the participants are only allowed to use the training data, obtained the highest F1 score of 96.03% and 92.05% in word segmentation and POS tagging. In the open modality, the participants can use whatever resource they have, with the highest F1 score of 96.34% and 92.56% in word segmentation and POS tagging. The scores on the blind test dataset decrease around 3 points, which shows that the out-of-vocabulary words still are the bottleneck for lexical analyzers.

The medical conversational system can relieve doctors’ burden and improve healthcare efficiency, especially during the COVID-19 pandemic. However, the existing medical dialogue systems have the problems of weak scalability, insufficient knowledge, and poor controllability. Thus, we propose a medical conversational question-answering (CQA) system based on the knowledge graph, namely MedConQA, which is designed as a pipeline framework to maintain high flexibility. Our system utilizes automated medical procedures, including medical triage, consultation, image-text drug recommendation, and record. Each module has been open-sourced as a tool, which can be used alone or in combination, with robust scalability. Besides, to conduct knowledge-grounded dialogues with users, we first construct a Chinese Medical Knowledge Graph (CMKG) and collect a large-scale Chinese Medical CQA (CMCQA) dataset, and we design a series of methods for reasoning more intellectually. Finally, we use several state-of-the-art (SOTA) techniques to keep the final generated response more controllable, which is further assured by hospital and professional evaluations. We have open-sourced related code, datasets, web pages, and tools, hoping to advance future research.

连动句是形如“NP+VP1+VP2”的句子,句中含有两个或两个以上的动词(或动词结构)且动词的施事为同一对象。相同结构的连动句可以表示多种不同的语义关系。本文基于前人对连动句中VP1和VP2之间的语义关系分类,标注了连动句语义关系数据集,基于神经网络完成了对连动句语义关系的识别。该方法将连动句语义识别任务进行分解,基于BERT进行编码,利用BiLSTM-CRF先识别出连动句中连动词(VP)及其主语(NP),再基于融合连动词信息的编码,利用BiLSTM-Attention对连动词进行关系判别,实验结果验证了所提方法的有效性。

汉语词语的离合现象是汉语中一种词语可分可合的特殊现象。本文采用字符级序列标注方法解决二字动词离合现象的自动识别问题,以避免中文分词及词性标注的错误传递,节省制定匹配规则与特征模板的人工开支。在训练过程中微调BERT中文预训练模型,获取面向目标任务的字符向量表示,并引入掩码机制对模型隐藏离用法中分离的词语,减轻词语本身对识别结果的影响,强化中间插入成分的学习,并对前后语素采用不同的掩码以强调其出现顺序,进而使模型具备了识别复杂及偶发性离用法的能力。为获得含有上下文信息的句子表达,将原始的句子表达与采用掩码的句子表达分别输入两个不同参数的BiLSTM层进行训练,最后采用CRF算法捕捉句子标签序列的依赖关系。本文提出的BERT MASK + 2BiLSTMs + CRF模型比现有最优的离合词识别模型提高了2.85%的F1值。

先秦汉语在汉语史研究上具有重要地位,然而以往的研究始终没有形成结构化的先秦词汇资源,难以满足古汉语信息处理和跨语言对比的研究需要。国际上以英文词网(WordNet)的义类架构为基础,已经建立了数十种语言的词网,已经成为多语言自然语言处理和跨语言对比的基础资源。本文综述了国内外各种词网的构建情况,特别是古代语言的词网和汉语词网,然后详细介绍了先秦词网的构建和校正过程,构建起了涵盖43591个词语、61227个义项、17975个义类的先秦汉语词网。本文还通过与古梵语词网的跨语言对比,尝试分析这两种古老语言在词汇上的共性和差异,初步验证先秦词网的有效性。

《古籍汉字分级字表》是基于大规模古籍文本语料库、为辅助学习者古籍文献阅读而研制的分级字表。该字表填补了古籍字表研究成果的空缺,依据各汉字学习优先级别的不同,实现了古籍汉字的等级划分,目前收录一级字105个,二级字340个,三级字555个。本文介绍了该字表研制的主要依据和基本步骤,并将其与传统识字教材“三百千”及《现代汉语常用字表》进行比较,验证了其收字的合理性。该字表有助于学习者优先掌握古籍文本常用字,提升古籍阅读能力,从而促进中华优秀传统文化的继承与发展。

The study of predicate frame is an important topic for semantic analysis. Abstract Meaning Representation (AMR) is an emerging graph based semantic representation of a sentence. Since core semantic roles defined in the predicate lexicon compose the backbone in an AMR graph, the construction of the lexicon becomes the key issue. The existing lexicons blur senses and frames of predicates, which needs to be refined to meet the tasks like word sense disambiguation and event extraction. This paper introduces the on-going project on constructing a novel predicate lexicon for Chinese AMR corpus. The new lexicon includes 14,389 senses and 10,800 frames of 8,470 words. As some senses can be aligned to more than one frame, and vice versa, we found the alignment between senses is not just one frame per sense. Explicit analysis is given for multiple aligned relations, which proves the necessity of the proposed lexicon for AMR corpus, and supplies real data for linguistic theoretical studies.

The 2020 Shared Task at the Conference for Computational Language Learning (CoNLL) was devoted to Meaning Representation Parsing (MRP) across frameworks and languages. Extending a similar setup from the previous year, five distinct approaches to the representation of sentence meaning in the form of directed graphs were represented in the English training and evaluation data for the task, packaged in a uniform graph abstraction and serialization; for four of these representation frameworks, additional training and evaluation data was provided for one additional language per framework. The task received submissions from eight teams, of which two do not participate in the official ranking because they arrived after the closing deadline or made use of additional training data. All technical information regarding the task, including system submissions, official results, and links to supporting resources and software are available from the task web site at: http://mrp.nlpl.eu

对话分析是智能客服、聊天机器人等自然语言对话应用的基础课题,而对话语料与常规书面语料有较大差异,存在大量的称谓、情感短语、省略、语序颠倒、冗余等复杂现象,对句法和语义分析器的影响较大,对话自动分析的准确率相对书面语料一直不高。其主要原因在于对多轮对话缺乏严整的形式化描写方式,不利于后续的分析计算。因此,本文在梳理国内外针对对话的标注体系和语料库的基础上,提出了基于抽象语义表示的篇章级多轮对话标注体系。具体探讨了了篇章级别的语义结构标注方法,给出了词语和概念关系的对齐方案,针对称谓语和情感短语增加了相应的语义关系和概念,调整了表示主观情感词语的论元结构,并对对话中一些特殊现象进行了规定,设计了人工标注平台,为大规模的多轮对话语料库标注与计算研究奠定基础。

疑问句的句法语义分析在搜索引擎、信息抽取和问答系统等领域有着广泛的应用。计算语言学多采取问句分类和句法分析相结合的方式来处理疑问句,精度和效率还不理想。而疑问句的语言学研究成果丰富,比如疑问句的结构类型、疑问焦点和疑问代词的非疑问用法等,但缺乏系统的形式化表示。本文致力于解决这一难题,采用基于图结构的汉语句子语义的整体表示方法—中文抽象语义表示(CAMR)来标注疑问句的语义结构,将疑问焦点和整句语义一体化表示出来。然后选取了宾州中文树库CTB8.0网络媒体语料、小学语文教材以及《小王子》中文译本的2万句语料中共计2071句疑问句,统计了疑问句的主要特点。统计表明,各种疑问代词都可以通过疑问概念amr-unknown和语义关系的组合来表示,能够完整地表示出疑问句的关键信息、疑问焦点和语义结构。最后,根据疑问代词所关联的语义关系,统计了疑问焦点的概率分布,其中原因、修饰语和受事的占比最高,分别占26.53%、16.73%以及16.44%。基于抽象语义表示的疑问句标注与分析可以为汉语疑问句研究提供基础理论与资源。

连动句是具有连动结构的句子,是汉语中的特殊句法结构,在现代汉语中十分常见且使用频繁。连动句语法结构和语义关系都很复杂,在识别中存在许多问题,对此本文针对连动句的识别问题进行了研究,提出了一种基于神经网络的连动句识别方法。本方法分两步:第一步,运用简单的规则对语料进行预处理;第二步,用文本分类的思想,使用BERT编码,利用多层CNN与BiLSTM模型联合提取特征进行分类,进而完成连动句识别任务。在人工标注的语料上进行实验,实验结果达到92.71%的准确率,F1值为87.41%。

作为信息抽取的一项核心子任务,实体关系抽取对于知识图谱、智能问答、语义搜索等自然语言处理应用都十分重要。关系抽取在于从非结构化文本中自动地识别实体之间具有的某种语义关系。该文聚焦句子级别的关系抽取研究,介绍用于关系抽取的主要数据集并对现有的技术作了阐述,主要分为:有监督的关系抽取、远程监督的关系抽取和实体关系联合抽取。我们对比用于该任务的各种模型,分析它们的贡献与缺 陷。最后介绍中文实体关系抽取的研究现状和方法。

兼语结构是汉语中常见的一种动词结构,由述宾短语与主谓短语共享兼语,结构复杂,给句法分析造成困难,因此兼语语料库构建及识别工作对于语义解析及下游任务都具有重要意义。但现存兼语语料库较少,面向中文AMR标注体系的兼语语料库构建仍处于空白阶段。针对这一现状,本文总结了一套兼语语料库标注规范,并构建了一定数量面向中文AMR标注体系的兼语语料库。基于构建的语料库,采用基于字符的神经网络模型识别兼语结构,并对识别结果以及未来的改进方向进行分析总结。

The basic tasks of ancient Chinese information processing include automatic sentence segmentation, word segmentation, part-of-speech tagging and named entity recognition. Tasks such as lexical analysis need to be based on sentence segmentation because of the reason that a plenty of ancient books are not punctuated. However, step-by-step processing is prone to cause multi-level diffusion of errors. This paper designs and implements an integrated annotation system of sentence segmentation and lexical analysis. The BiLSTM-CRF neural network model is used to verify the generalization ability and the effect of sentence segmentation and lexical analysis on different label levels on four cross-age test sets. Research shows that the integration method adopted in ancient Chinese improves the F1-score of sentence segmentation, word segmentation and part of speech tagging. Based on the experimental results of each test set, the F1-score of sentence segmentation reached 78.95, with an average increase of 3.5%; the F1-score of word segmentation reached 85.73%, with an average increase of 0.18%; and the F1-score of part-of-speech tagging reached 72.65, with an average increase of 0.35%.

Abstract Meaning Representation (AMR) is a meaning representation framework in which the meaning of a full sentence is represented as a single-rooted, acyclic, directed graph. In this article, we describe an on-going project to build a Chinese AMR (CAMR) corpus, which currently includes 10,149 sentences from the newsgroup and weblog portion of the Chinese TreeBank (CTB). We describe the annotation specifications for the CAMR corpus, which follow the annotation principles of English AMR but make adaptations where needed to accommodate the linguistic facts of Chinese. The CAMR specifications also include a systematic treatment of sentence-internal discourse relations. One significant change we have made to the AMR annotation methodology is the inclusion of the alignment between word tokens in the sentence and the concepts/relations in the CAMR annotation to make it easier for automatic parsers to model the correspondence between a sentence and its meaning representation. We develop an annotation tool for CAMR, and the inter-agreement as measured by the Smatch score between the two annotators is 0.83, indicating reliable annotation. We also present some quantitative analysis of the CAMR corpus. 46.71% of the AMRs of the sentences are non-tree graphs. Moreover, the AMR of 88.95% of the sentences has concepts inferred from the context of the sentence but do not correspond to a specific word.

Ellipsis is very common in language. It’s necessary for natural language processing to restore the elided elements in a sentence. However, there’s only a few corpora annotating the ellipsis, which draws back the automatic detection and recovery of the ellipsis. This paper introduces the annotation of ellipsis in Chinese sentences, using a novel graph-based representation Abstract Meaning Representation (AMR), which has a good mechanism to restore the elided elements manually. We annotate 5,000 sentences selected from Chinese TreeBank (CTB). We find that 54.98% of sentences have ellipses. 92% of the ellipses are restored by copying the antecedents’ concepts. and 12.9% of them are the new added concepts. In addition, we find that the elided element is a word or phrase in most cases, but sometimes only the head of a phrase or parts of a phrase, which is rather hard for the automatic recovery of ellipsis.

This paper presents the first AMR parser built on the Chinese AMR bank. By applying a transition-based AMR parsing framework to Chinese, we first investigate how well the transitions first designed for English AMR parsing generalize to Chinese and provide a comparative analysis between the transitions for English and Chinese. We then perform a detailed error analysis to identify the major challenges in Chinese AMR parsing that we hope will inform future research in this area.