skip to main content
research-article

Improved Discourse Parsing with Two-Step Neural Transition-Based Model

Published: 11 January 2018 Publication History

Abstract

Discourse parsing aims to identify structures and relationships between different discourse units. Most existing approaches analyze a whole discourse at once, which often fails in distinguishing long-span relations and properly representing discourse units. In this article, we propose a novel parsing model to analyze discourse in a two-step fashion with different feature representations to characterize intra sentence and inter sentence discourse structures, respectively. Our model works in a transition-based framework and benefits from a stack long short-term memory neural network model. Experiments on benchmark tree banks show that our method outperforms traditional 1-step parsing methods in both English and Chinese.

References

[1]
Miguel Ballesteros, Chris Dyer, and Noah A. Smith. 2015. Improved transition-based parsing by modeling characters instead of words with LSTMs. In EMNLP’15, Lisbon, Portugal. 349--359.
[2]
Or Biran and Kathleen McKeown. 2013. Aggregated word pair features for implicit discourse relation disambiguation. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL’13), 4-9 August 2013, Sofia, Bulgaria, Volume 2: Short Papers. 69--73. http://aclweb.org/anthology/P/P13/P13-2013.pdf.
[3]
Chloé Braud, Maximin Coavoux, and Anders Søgaard. 2017. Cross-lingual RST discourse parsing. CoRR abs/1701.02946 (2017). http://arxiv.org/abs/1701.02946
[4]
Lynn Carlson, Daniel Marcu, and Mary Ellen Okurovsky. 2001. Building a discourse-tagged corpus in the framework of rhetorical structure theory. In Proceedings of the SIGDIAL’01 Workshop, The 2nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, Saturday, September 1, 2001 to Sunday, September 2, 2001, Aalborg, Denmark. http://aclweb.org/anthology/W/W01/W01-1605.pdf.
[5]
Danqi Chen and Christopher D. Manning. 2014. A fast and accurate dependency parser using neural networks. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP’14), October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL. 740--750. http://aclweb.org/anthology/D/D14/D14-1082.pdf.
[6]
Jifan Chen, Qi Zhang, Pengfei Liu, Xipeng Qiu, and Xuanjing Huang. 2016. Implicit discourse relation detection via a deep architecture with gated relevance network. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL’16), August 7-12, 2016, Berlin, Germany, Volume 1: Long Papers. http://aclweb.org/anthology/P/P16/P16-1163.pdf.
[7]
Michael Collins and Brian Roark. 2004. Incremental parsing with the perceptron algorithm. In ACL’04, 21-26 July, 2004, Spain. 111--118.
[8]
Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, and Noah A. Smith. 2015. Transition-based dependency parsing with stack long short-term memory. In ACL’15, Volume 1. 334--343.
[9]
Vanessa Wei Feng and Graeme Hirst. 2012. Text-level discourse parsing with rich linguistic features. In ACL’12, July 8-14, 2012, Jeju Island, Korea - Volume 1: Long Papers. 60--68. http://www.aclweb.org/anthology/P12-1007.
[10]
Vanessa Wei Feng and Graeme Hirst. 2014. A linear-time bottom-up discourse parser with constraints and post-editing. In ACL’14, Baltimore, MD, USA, Volume 1. 511--521.
[11]
David A. Ferrucci, Eric W. Brown, Jennifer Chu-Carroll, James Fan, David Gondek, Aditya Kalyanpur, Adam Lally, J. William Murdock, Eric Nyberg, John M. Prager, Nico Schlaefer, and Christopher A. Welty. 2010. Building Watson: An overview of the deepQA project. AI Magazine 31, 3, 59--79.
[12]
Xavier Glorot, Antoine Bordes, and Yoshua Bengio. Deep sparse rectifier neural networks. In AISTATS’11, Fort Lauderdale, USA, April 11-13, 2011.
[13]
Udo Hahn. 2002. The theory and practice of discourse parsing and summarization by Daniel Marcu. Computational Linguistics 28, 1, 81--83.
[14]
Hugo Hernault, Helmut Prendinger, David A. duVerle, and Mitsuru Ishizuka. 2010. HILDA: A discourse parser using support vector machine classification. D8D 1, 3, 1--33.
[15]
Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation 9, 8, 1735--1780.
[16]
Yangfeng Ji, Gongbo Zhang, and Jacob Eisenstein. 2015. Closing the gap: Domain adaptation from explicit to implicit discourse relations. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP’15), Lisbon, Portugal, September 17-21, 2015. 2219--2224. http://aclweb.org/anthology/D/D15/D15-1264.pdf.
[17]
Yanyan Jia, Yansong Feng, Bingfeng Luo, Yuan Ye, Tianyang Liu, and Dongyan Zhao. 2016. Transition-based discourse parsing with multilayer stack long short term memory. In Proceedings of the Natural Language Understanding and Intelligent Applications - 5th CCF Conference on Natural Language Processing and Chinese Computing (NLPCC’16), and 24th International Conference on Computer Processing of Oriental Languages (ICCPOL’16), Kunming, China, December 2-6, 2016.360--373.
[18]
Shafiq R. Joty, Giuseppe Carenini, Raymond T. Ng, and Yashar Mehdad. 2013. Combining intra- and multi-sentential rhetorical parsing for document-level discourse analysis. In ACL’13. 486--496.
[19]
Shafiq R. Joty and Alessandro Moschitti. 2014. Discriminative reranking of discourse parses using tree kernels. In EMNLP’14, October 25-29, 2014, Doha, Qatar. 2049--2060. http://aclweb.org/anthology/D/D14/D14-1219.pdf.
[20]
Huong LeThanh. 2004. Generating discourse structures for written texts. Proceedings of the 20th International Conference on Computational Linguistics.
[21]
Jiwei Li, Rumeng Li, and Eduard H. Hovy. 2014. Recursive deep models for discourse parsing. In EMNLP’14, October 25-29, 2014. 2061--2069. http://aclweb.org/anthology/D/D14/D14-1220.pdf.
[22]
Sujian Li, Liang Wang, Ziqiang Cao, and Wenjie Li. 2014. Text-level discourse dependency parsing. In ACL’14, Baltimore, MD, Volume 1. 25--35.
[23]
Yancui Li, Jing Sun, Fang Kong, and Guodong Zhou. 2014. Building Chinese discourse corpus with connective-driven dependency tree structure. In EMNLP’14. http://www.aclweb.org/anthology/D/D14/D14-1224.pdf.
[24]
Ziheng Lin, Min-Yen Kan, and Hwee Tou Ng. 2009. Recognizing implicit discourse relations in the Penn discourse treebank. In EMNLP’09, 6-7 August 2009, Singapore. 343--351. http://www.aclweb.org/anthology/D09-1036.
[25]
Yang Liu and Sujian Li. 2016. Recognizing implicit discourse relations via repeated reading: Neural networks with multi-level attention. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP’16), Austin, Texas, USA, November 1-4, 2016. 1224--1233. http://aclweb.org/anthology/D/D16/D16-1130.pdf.
[26]
D. L. Long, C. L. Johns, and E. Jonathan. 2012. A memory-retrieval view of discourse representation: The recollection and familiarity of text ideas. Language and Cognitive Processes 27, 6, 821--843.
[27]
Annie Louis, Aravind K. Joshi, and Ani Nenkova. Discourse indicators for content selection in summarization. In SIGDIAL’10.
[28]
G. McKoon and R. Ratcliff. 1998. Memory-based language processing: Psycholinguistic research in the 1990s. Annual Review of Psychology, vol. 49, 25–42.
[29]
Jane Morris and Graeme Hirst. 1991. Lexical cohesion computed by thesaural relations as an indicator of the structure of text. Computational Linguistics 17, 1, 21--48.
[30]
Joakim Nivre. 2009. Non-projective dependency parsing in expected linear time. In ACL’09. http://www.aclweb.org/anthology/P09-1040.
[31]
Joakim Nivre and Mario Scholz. 2004. Deterministic dependency parsing of English text. In COLING 2’04, 23-27 August 2004, Geneva, Switzerland.
[32]
Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP’14), October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, A Special Interest Group of the ACL. 1532--1543. http://aclweb.org/anthology/D/D14/D14-1162.pdf.
[33]
Emily Pitler, Annie Louis, and Ani Nenkova. 2009. Automatic sense prediction for implicit discourse relations in text. In ACL’09, Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the AFNLP, 2-7 August 2009, Singapore. 683--691. http://www.aclweb.org/anthology/P09-1077.
[34]
Emily Pitler, Mridhula Raghupathy, Hena Mehta, Ani Nenkova, Alan Lee, and Aravind K. Joshi. 2008. Easily identifiable discourse relations. In COLING’08, 22nd International Conference on Computational Linguistics, Posters Proceedings, 18-22 August 2008, Manchester, UK. 87--90. http://www.aclweb.org/anthology/C08-2022
[35]
Richard Socher, Andrej Karpathy, Quoc V. Le, Christopher D. Manning, and Andrew Y. Ng. 2014. Grounded compositional semantics for finding and describing images with sentences. TACL 2, 207--218.
[36]
Kimberly D. Voll and Maite Taboada. 2007. Not all words are created equal: Extracting semantic orientation as a function of adjective relevance. In Proceedings of AI’07, Gold Coast, Australia, December 2-6, 2007. 337--346.
[37]
Yuping Zhou and Nianwen Xue. 2012. PDTB-style discourse annotation of Chinese text. In the 50th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, July 8-14, 2012, Jeju Island, Korea - Volume 1: Long Papers. 69--77. http://www.aclweb.org/anthology/P12-1008.
[38]
R. A. Zwaan and Gabriel A. Radvansky. 1998. Situation models in language comprehension and memory. Sychological Bulletin 123, 2.

Cited By

View all
  • (2022)A survey of discourse parsingFrontiers of Computer Science10.1007/s11704-021-0500-z16:5Online publication date: 20-Jan-2022
  • (2022)Two-Layer Context-Enhanced Representation for Better Chinese Discourse ParsingNatural Language Processing and Chinese Computing10.1007/978-3-031-17120-8_4(43-54)Online publication date: 24-Sep-2022
  • (2020)QuAChIE: Question Answering based Chinese Information Extraction SystemProceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3397271.3401411(2177-2180)Online publication date: 25-Jul-2020
  • Show More Cited By

Index Terms

  1. Improved Discourse Parsing with Two-Step Neural Transition-Based Model

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Transactions on Asian and Low-Resource Language Information Processing
    ACM Transactions on Asian and Low-Resource Language Information Processing  Volume 17, Issue 2
    June 2018
    134 pages
    ISSN:2375-4699
    EISSN:2375-4702
    DOI:10.1145/3160862
    Issue’s Table of Contents
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 11 January 2018
    Accepted: 01 October 2017
    Revised: 01 August 2017
    Received: 01 April 2017
    Published in TALLIP Volume 17, Issue 2

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Discourse parsing
    2. LSTM
    3. dependency parsing
    4. transition-based system

    Qualifiers

    • Research-article
    • Research
    • Refereed

    Funding Sources

    • National High Technology R8D Program of China
    • Natural Science Foundation of China
    • IBM Research

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)8
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 17 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2022)A survey of discourse parsingFrontiers of Computer Science10.1007/s11704-021-0500-z16:5Online publication date: 20-Jan-2022
    • (2022)Two-Layer Context-Enhanced Representation for Better Chinese Discourse ParsingNatural Language Processing and Chinese Computing10.1007/978-3-031-17120-8_4(43-54)Online publication date: 24-Sep-2022
    • (2020)QuAChIE: Question Answering based Chinese Information Extraction SystemProceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3397271.3401411(2177-2180)Online publication date: 25-Jul-2020
    • (2020)Dynamic Updating of the Knowledge Base for a Large-Scale Question Answering SystemACM Transactions on Asian and Low-Resource Language Information Processing10.1145/337770819:3(1-13)Online publication date: 20-Feb-2020
    • (2020)Syntax-Guided Sequence to Sequence Modeling for Discourse SegmentationNatural Language Processing and Chinese Computing10.1007/978-3-030-60457-8_8(95-107)Online publication date: 2-Oct-2020

    View Options

    Login options

    Full Access

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media