Answer Ranking with Discourse Structure Feature

For the complex questions of Chinese question answering system, we propose an answer extraction method with discourse structure feature combination. This method uses the relevance of questions and answers to learn to rank the answers. Firstly, the method analyses questions to generate the query string, and then submits the query string to search engines to retrieve relevant documents. Sec- ondly, the method makes retrieved documents seg- mentation and identifies the most relevant candidate answers, in addition, it uses the rhetorical relations of rhetorical structure theory to analyze the relationship to determine the inherent relationship between para- graphs or sentences and generate the answer candi- date paragraphs or sentences. Thirdly, we construct the answer ranking model,, and extract five feature groups and adopt Ranking Support Vector Machine （SVM） algorithm to train ranking model. Finally, it re-ranks the answers with the training model and fred the optimal answers. Experiments show that the proposed method combined with discourse structure features can effectively improve the answer extrac- ting accuracy and the quality of non-factoid an- swers. The Mean Reciprocal Rank （MRR） of the an- swer extraction reaches 69.53%.

A COMPARATIVE STUDY OF THE CLASSROOM DISCOURSE STRUCTURES IN THE COLLEGE ENGLISH CLASSES IN CHINA

The present study, using Discourse Analysis method, makes a comparative study of the interactive features of two groups of college English teaching classes, one instructed by native speakers of English, the other by Chinese teachers of English. It has been found that TST (Teacher-Student-Teacher) structure occurs more frequently in the classes taught by Chinese teachers of English. It is suggested that Chinese teachers put their classes under stricter control than native English teachers do.

A Case Study on the Pattern of Classroom Discourse in Teaching Chinese as a Foreign Language

Based on the IRF(initiation,response,and feedback)classroom discourse structure model proposed by Sinclair and Coulthard,this research analyzes and studies the actual corpus of Chinese classroom teaching in Thailand,focusing on the structural model of teacher-student communication discourse,mainly from two aspects of teachers'feedback.On the one hand,it investigates whether IRF is fully applicable to Chinese classroom teaching and whether there are special situations to it.On the other hand,it attempts to summarize the discourse structure model of Chinese classroom teaching and explores the application of the research results in helping Chinese teachers improve their teaching quality in hope that constructive suggestions can be proposed for teaching Chinese as a foreign language.

Top-down Text-Level Discourse Rhetorical Structure Parsing with Bidirectional Representation Learning

Early studies on discourse rhetorical structure parsing mainly adopt bottom-up approaches,limiting the parsing process to local information.Although current top-down parsers can better capture global information and have achieved particular success,the importance of local and global information at various levels of discourse parsing is differ-ent.This paper argues that combining local and global information for discourse parsing is more sensible.To prove this,we introduce a top-down discourse parser with bidirectional representation learning capabilities.Existing corpora on Rhetorical Structure Theory(RST)are known to be much limited in size,which makes discourse parsing very challenging.To alleviate this problem,we leverage some boundary features and a data augmentation strategy to tap the potential of our parser.We use two methods for evaluation,and the experiments on the RST-DT corpus show that our parser can pri-marily improve the performance due to the effective combination of local and global information.The boundary features and the data augmentation strategy also play a role.Based on gold standard elementary discourse units(EDUs),our pars-er significantly advances the baseline systems in nuclearity detection,with the results on the other three indicators(span,relation,and full)being competitive.Based on automatically segmented EDUs,our parser still outperforms previous state-of-the-artwork.

A survey of discourse parsing

Discourse parsing is an important research area in natural language processing(NLP),which aims to parse the discourse structure of coherent sentences.In this survey,we introduce several different kinds of discourse parsing tasks,mainly including RST-style discourse parsing,PDTB-style discourse parsing,and discourse parsing for multiparty dialogue.For these tasks,we introduce the classical and recent existing methods,especially neural network approaches.After that,we describe the applications of discourse parsing for other NLP tasks,such as machine reading comprehension and sentiment analysis.Finally,we discuss the future trends of the task.