Abstract
Discourse parsing is a challenging task and plays a critical role in discourse analysis. In this paper, we focus on building an end-to-end PDTB-style explicit discourse parser via structured perceptron by decomposing it into two components, i.e., a connective labeler, which identifies connectives from a text and determines their senses in classifying discourse relationship, and an argument labeler, which identifies corresponding arguments for a given connective. Particularly, to reduce error propagation and incorporate the interaction between the two components, a joint learning approach via structured perceptron is proposed. Evaluation on the PDTB corpus shows that our two-components explicit discourse parser can achieve comparable performance with the state-of-the-art one. It also shows that our joint learning approach can significantly outperform the pipeline ones.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barzilay, R., Lapata, M.: Modeling local coherence: An entity-based approach. In: Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL 2005), pp. 141–148. Association for Computational Linguistics, Ann Arbor (2005), http://www.aclweb.org/anthology/P05-1018
Collins, M.: Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In: Proceedings of the ACL 2002 Conference on Empirical Methods in Natural Language Processing, vol. 10, pp. 1–8. Association for Computational Linguistics (2002)
Collins, M., Roark, B.: Incremental parsing with the perceptron algorithm. In: Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, p. 111. Association for Computational Linguistics (2004)
Dines, N., Lee, A., Miltsakaki, E., Prasad, R., Joshi, A., Webber, B.: Attribution and the (non-)alignment of syntactic and discourse arguments of connectives. In: Proceedings of the Workshop on Frontiers in Corpus Annotations II: Pie in the Sky, CorpusAnno 2005, pp. 29–36. Association for Computational Linguistics, Stroudsburg (2005), http://dl.acm.org/citation.cfm?id=1608829.1608834
Elwell, R., Baldridge, J.: Discourse connective argument identification with connective specific rankers. In: 2008 IEEE International Conference on Semantic Computing, pp. 198–205 (2008)
Ghosh, S.: End-to-End Discourse Parsing with Cascaded Structured Prediction. Ph.D. thesis, University of Trento (2012)
Ghosh, S., Johansson, R., Riccardi, G., Tonelli, S.: Shallow discourse parsing with conditional random fields. In: Proceedings of 5th International Joint Conference on Natural Language Processing, pp. 1071–1079. Asian Federation of Natural Language Processing, Chiang Mai (2011), http://www.aclweb.org/anthology/I11-1120
Huang, L., Fayong, S., Guo, Y.: Structured perceptron with inexact search. In: Proceedings of NAACL 2012 (2012)
Lin, Z., Liu, C., Ng, H.T., Kan, M.Y.: Combining coherence models and machine translation evaluation metrics for summarization evaluation. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 1006–1014. Association for Computational Linguistics, Jeju Island (2012), http://www.aclweb.org/anthology/P12-1106
Lin, Z., Ng, H.T., Kan, M.Y.: A pdtb-styled end-to-end discourse parser. Technical report, School of Computing. National University of Singapore (2010)
Lin, Z., Ng, H.T., Kan, M.Y.: Automatically evaluating text coherence using discourse relations. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 997–1006. Association for Computational Linguistics (2011)
Lin, Z., Ng, H.T., Kan, M.Y.: A pdtb-styled end-to-end discourse parser. Natural Language Engineering FirstView, 1–34 (August 2013), http://journals.cambridge.org/article_S1351324912000307
Marcus, M., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of English: The penn treebank. Computational Linguistics 19(2), 313–330 (1993)
Meyer, T., Webber, B.: Implicitation of discourse connectives in (machine) translation. In: Proceedings of the Workshop on Discourse in Machine Translation, pp. 19–26. Association for Computational Linguistics, Sofia (2013), http://www.aclweb.org/anthology/W13-3303
Miltsakaki, E., Prasad, R., Joshi, A., Webber, B.: The penn discourse treebank, pp. 2237–2240 (2004), http://www.lrec-conf.org/proceedings/lrec2004/pdf/618
Ng, J.P., Kan, M.Y., Lin, Z., Feng, W., Chen, B., Su, J., Tan, C.L.: Exploiting discourse analysis for article-wide temporal classification. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 12–23. Association for Computational Linguistics, Seattle (2013), http://www.aclweb.org/anthology/D13-1002
The PDTB Research Group: the Penn Discourse Treebank 2.0 Annotation Manual (December 2007)
Pitler, E., Nenkova, A.: Using syntax to disambiguate explicit discourse connectives in text. In: Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pp. 13–16. Association for Computational Linguistics, Suntec (2009), http://www.aclweb.org/anthology/P/P09/P09-2004
Prasad, R., Dinesh, N., Lee, A., Miltsakaki, E., Robaldo, L., Joshi, A., Webber, B.: The penn discourse treebank 2.0, pp. 2961–2968 (2008), http://www.lrec-conf.org/proceedings/lrec2008/pdf/754
Prasad, R., Joshi, A., Webber, B.: Exploiting scope for shallow discourse parsing. In: Calzolari, N. (Conference Chair), Choukri, K., Maegaard, B., Mariani, J., Odijk, J., Piperidis, S., Rosner, M., Tapias, D. (eds.) Proceedings of the Seventh Conference on International Language Resources and Evaluation (LREC 2010). European Language Resources Association (ELRA), Valletta (2010)
Webber, B.: D-ltag: Extending lexicalized tag to discourse. Cognitive Science 28(5), 751–779 (2004)
Wellner, B., Pustejovsky, J.: Automatically identifying the arguments of discourse connectives. In: Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 92–101. Association for Computational Linguistics, Prague (2007), http://www.aclweb.org/anthology/D/D07/D07-1010
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Li, S., Kong, F., Zhou, G. (2014). A Joint Learning Approach to Explicit Discourse Parsing via Structured Perceptron. In: Sun, M., Liu, Y., Zhao, J. (eds) Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. NLP-NABD CCL 2014 2014. Lecture Notes in Computer Science(), vol 8801. Springer, Cham. https://doi.org/10.1007/978-3-319-12277-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-12277-9_7
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12276-2
Online ISBN: 978-3-319-12277-9
eBook Packages: Computer ScienceComputer Science (R0)