Constructing Chinese Macro Discourse Tree via Multiple Views and Word Pair Similarity

Macro-discourse structure recognition is an important task in macro-discourse analysis. At present, the research on macro-discourse analysis mostly uses the manual features (e.g., the position features), and ignores the semantic information in topic level. In this paper, we first propose a multi-view neural network to construct Chinese macro discourse trees from three views, i.e., the word view, the context view and the topic view. Besides, we propose a novel word-pair similarity mechanism to capture the interaction among the discourse units and the topic. The experimental results on MCDTB, a Chinese discourse corpus, show that our model outperforms the baseline significantly.

[1]  Guodong Zhou,et al.  Joint Modeling of Structure Identification and Nuclearity Recognition in Macro Chinese Discourse Treebank , 2018, COLING.

[2]  Nicholas Asher,et al.  How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DT , 2017, EMNLP.

[3]  Boris A. Galitsky.  Building Dialogue Structure from Discourse Tree of a Question , 2018, AAAI Workshops.

[4]  Shafiq R. Joty,et al.  Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis , 2013, ACL.

[5]  Nicholas Asher,et al.  A Dependency Perspective on RST Discourse Parsing and Evaluation , 2018, CL.

[6]  Mitsuru Ishizuka,et al.  HILDA: A Discourse Parser Using Support Vector Machine Classification , 2010, Dialogue Discourse.

[7]  Daniel Marcu,et al.  A Decision-Based Approach to Rhetorical Parsing , 1999, ACL.

[8]  Feng Jiang,et al.  Building a Macro Chinese Discourse Treebank , 2018, LREC.

[9]  William C. Mann,et al.  Rhetorical Structure Theory: Toward a functional theory of text organization , 1988 .

[10]  Guodong Zhou,et al.  Employing Text Matching Network to Recognise Nuclearity in Chinese Discourse , 2018, COLING.

[11]  Guodong Zhou,et al.  Recognizing Macro Chinese Discourse Structure on Label Degeneracy Combination Model , 2018, NLPCC.

[12]  Alex Lascarides,et al.  Combining Hierarchical Clustering and Machine Learning to Predict High-Level Discourse Structure , 2004, COLING.

[13]  Hwee Tou Ng,et al.  Recognizing Implicit Discourse Relations in the Penn Discourse Treebank , 2009, EMNLP.

[14]  Qi Li,et al.  Discourse Parsing with Attention-based Hierarchical Neural Networks , 2016, EMNLP.

[15]  Stefan Feuerriegel,et al.  Sentiment analysis based on rhetorical structure theory: Learning deep neural networks from discourse trees , 2017, Expert Syst. Appl..

[16]  William C. Mann,et al.  Relational propositions in discourse , 1986 .

[17]  Jianwu Dang,et al.  Implicit Discourse Relation Recognition using Neural Tensor Network with Interactive Attention and Sparse Learning , 2018, COLING.

[18]  Dongyan Zhao,et al.  Modeling discourse cohesion for discourse parsing via memory network , 2018, ACL.

[19]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[20]  Graeme Hirst,et al.  A Linear-Time Bottom-Up Discourse Parser with Constraints and Post-Editing , 2014, ACL.

[21]  Guodong Zhou,et al.  MCDTB: A Macro-level Chinese Discourse TreeBank , 2018, COLING.