Interpretation of Chinese Discourse Connectives for Explicit Discourse Relation Recognition

This paper addresses the specific features of Chinese discourse connectives, including types (word-pair and single-word), linking directions (forward and backward linking), positions and ambiguous degrees, and discusses how they affect the discourse relation recognition. A semisupervised learning method is proposed to learn the probability distributions of discourse functions of connectives from a small labeled dataset and a big unlabeled dataset. The statistics learned from the dataset demonstrates some interesting linguistic phenomena such as connective synonyms sharing similar distributions, multiple discourse functions of connectives, and couple-linking elements providing strong clues for discourse relation resolution.

[1]  Alex Lascarides,et al.  Edinburgh Research Explorer Using automatically labelled examples to classify rhetorical relations: an assessment , 2022 .

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  Laurence Danlos,et al.  LEXCONN: A French Lexicon of Discourse Connectives , 2010 .

[4]  Eduard Hovy,et al.  Parsimonious or Profligate: How Many and Which Discourse Structure Relations? , 1992 .

[5]  Hsin-Hsi Chen.  The Contextual Analysis of Chinese Sentences with Punctuation Marks , 1994 .

[6]  Hsin-Hsi Chen,et al.  Chinese Discourse Relation Recognition , 2011, IJCNLP.

[7]  Alex Lascarides,et al.  Lexical Disambiguation in a Discourse Context , 1995, J. Semant..

[8]  Leon Derczynski,et al.  Temporal Signals Help Label Temporal Relations , 2013, ACL.

[9]  Ani Nenkova,et al.  Using Syntax to Disambiguate Explicit Discourse Connectives in Text , 2009, ACL.

[10]  Hsin-Hsi Chen,et al.  Contingency and Comparison Relation Labeling and Structure Prediction in Chinese Sentences , 2012, SIGDIAL Conference.

[11]  C. Pollard,et al.  Center for the Study of Language and Information , 2022 .

[12]  Livio Robaldo,et al.  The Penn Discourse TreeBank 2.0. , 2008, LREC.

[13]  Yuping Zhou,et al.  PDTB-style Discourse Annotation of Chinese Text , 2012, ACL.

[14]  Hsin-Hsi Chen,et al.  Analyses of the Association between Discourse Relation and Sentiment Polarity with a Chinese Human-Annotated Corpus , 2013, LAW@ACL.

[15]  Hwee Tou Ng,et al.  Automatically Evaluating Text Coherence Using Discourse Relations , 2011, ACL.

[16]  Wei Gao,et al.  Unsupervised Discovery of Discourse Relations for Eliminating Intra-sentence Polarity Ambiguities , 2011, EMNLP.

[17]  Leo G. M. Noordman,et al.  Toward a taxonomy of coherence relations , 1992 .

[18]  Fei Wang,et al.  Exploiting Discourse Relations for Sentiment Analysis , 2012, COLING.

[19]  Hsin-Hsi Chen,et al.  Development of a Web-Scale Chinese Word N-gram Corpus with Parts of Speech Information , 2012, LREC.

[20]  J. Hobbs.  On the coherence and structure of discourse , 1985 .

[21]  Bruno Cartoni,et al.  Annotating the meaning of discourse connectives by looking at their translation: The translation-spotting technique , 2013, Dialogue Discourse.

[22]  Tyne Liang,et al.  以語料為基礎的中文語篇連貫關係自動標記 (Corpus-Based Coherence Relation Tagging in Chinese Discourse) [In Chinese] , 2006, ROCLING.

[23]  Charles N. Li,et al.  Mandarin Chinese: A Functional Reference Grammar , 1989 .

[24]  Wei Gao,et al.  Cross-Lingual Identification of Ambiguous Discourse Connectives for Resource-Poor Language , 2012, COLING.

[25]  Edward Gibson,et al.  Representing Discourse Coherence: A Corpus-Based Study , 2005, CL.

[26]  Ben Hutchinson,et al.  Acquiring the Meaning of Discourse Markers , 2004, ACL.

[27]  Hsin-Hsi Chen,et al.  An Annotation System for Development of Chinese Discourse Corpus , 2012, COLING.

[28]  Ludovic Tanguy,et al.  An empirical resource for discovering cognitive principles of discourse organisation: the ANNODIS corpus , 2012, LREC.

[29]  L. Polanyi.  A formal model of the structure of discourse , 1988 .