Abstract
This paper presents a mutual learning method using hierarchical deep semantics for the classification of implicit discourse relations in English. With the absence of explicit discourse markers, traditional discourse techniques mainly concentrate on discrete linguistic features in this task, which always leads to data sparse problem. To relieve this problem, we propose a mutual learning neural model which makes use of multilevel semantic information together, including the distribution of implicit discourse relations, the semantics of arguments and the co-occurrence of words. During the training process, the predicted target of the model which is the probability of the discourse relation type, and the distributed representation of semantic components are learnt jointly and optimized mutually. The results of both binary and multiclass identification show that this method outperforms previous works since the mutual learning strategy can distinguish Expansion type from the others efficiently.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Pitler, E., et al.: Easily identifiable discourse relations. In: International Conference on Computational Linguistics, Posters Proceedings, COLING 2008, 18–22 August 2008, Manchester, UK (2008)
Park, J., Cardie, C.: Improving implicit discourse relation recognition through feature set optimization. In: International Conference on Computational Science and Engineering (2009)
Prasad, R., Miltsakaki, E., Dinesh, N., Lee, A., Joshi, A.: The Penn discourse treebank 2.0 annotation manual. In: Proceedings of LREC, vol. 24, p. 2961 (2008)
Bengio, Y., Schwenk, H., Senécal, J.S., Morin, F., Gauvain, J.L.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137 (2003)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, vol. 26, p. 3111 (2013)
Biran, O., Mckeown, K.: Aggregated word pair features for implicit discourse relation disambiguation. In: Meeting of the Association for Computational Linguistics, vol. 69 (2013)
Marcu, D., Echihabi, A.: An unsupervised approach to recognizing discourse relations, Philadelphia, Pennsylvania, USA, 368 p. (2002)
Soricut, R., Marcu, D.: Sentence level discourse parsing using syntactic and lexical information. In: Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology, vol. 149 (2003)
Carlson, L., Marcu, D., Okurowski, M.E.: Building a Discourse-Tagged Corpus in the Framework of Rhetorical Structure Theory. Springer, Netherlands (2003)
Wellner, B., Pustejovsky, J., Havasi, C., Rumshisky, A., Saurí, R.: Classification of discourse coherence relations: an exploratory study using multiple knowledge sources. In: Proceedings of 7th SIGDIAL Workshop on Discourse and Dialogue, vol. 117 (2006)
Wolf, F., Gibson, E.: Representing discourse coherence: a corpus-based study. Comput. Linguist. 32, 249 (2005)
Pitler E., Louis A., Nenkova A.: Automatic sense prediction for implicit discourse relations in text. In: ACL 2009, Proceedings of the Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing of the AFNLP, 2–7 August 2009, Singapore, vol. 683 (2009)
Lin, Z., Kan, M.Y., Ng, H.T.: Recognizing implicit discourse relations in the Penn Discourse Treebank. In: Conference on Empirical Methods in Natural Language Processing, vol. 343 (2009)
Wang, W.T., Su, J., Tan, C.L.: Kernel based discourse relation recognition with temporal ordering information. In: ACL 2010, Proceedings of the Meeting of the Association for Computational Linguistics, 11–16 July 2010, Uppsala, Sweden, vol. 710 (2010)
Zhou, Z.M., Xu, Y., Niu, Z.Y., Lan, M., Su, J., Tan, C.L.: Predicting discourse connectives for implicit discourse relation recognition. In: International Conference on Computational Linguistics: Posters (2010)
Lan, M., Xu, Y., Niu, Z.: Leveraging synthetic discourse data via multi-task learning for implicit discourse relation recognition. In: Meeting of the Association for Computational Linguistics (2013)
Fisher, R., Simmons, R.: Spectral semi-supervised discourse relation classification, Beijing, China, 89 p. (2015)
Braud, C.E., Denis, P.: Combining natural and artificial examples to improve implicit discourse relation identification, Dublin, Ireland, 1694 p. (2014)
Socher, R., Perelygin, A., Wu, J.Y., Chuang, J., Manning, C.D., Ng, A.Y., Potts, C.: Recursive deep models for semantic compositionality over a sentiment treebank (2013)
Yang, M., Cui, T., Tu, W.: Ordering-sensitive and semantic-aware topic modeling. In: Computer Science (2015)
Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. In: Computer Science, vol. 4, p. 1188 (2014)
Rutherford, A.T., Xue, N.: Discovering implicit discourse relations through Brown cluster pair representation and conference patterns, vol. 645 (2014)
Rutherford, A., Xue, N.: Improving the inference of implicit discourse relations via classifying explicit discourse connectives. In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2015)
Marcus, M.P., Marcinkiewicz, M.A., Santorini, B.: Building a large annotated corpus of English: the Penn treebank. Comput. Linguist. 19, 313 (1993)
Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing contextual polarity in phrase-level sentiment analysis. Int. J. Comput. Appl. 7, 347 (2005)
Stone, P.J.: The General Inquirer: A Computer Approach to Content Analysis. M.I.T. Press, Cambridge (1966)
Acknowledgment
The authors would like to thank the organizers of NLPCC-ICCPOL 2016 and the reviewers for their helpful suggestions. This research is supported by the National Natural Science Foundation of China (61202244, 61502259) and the National Basic Research Program of China (973 Program, 2013CB329303).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
She, X., Jian, P., Zhang, P., Huang, H. (2016). Leveraging Hierarchical Deep Semantics to Classify Implicit Discourse Relations via Mutual Learning Method. In: Lin, CY., Xue, N., Zhao, D., Huang, X., Feng, Y. (eds) Natural Language Understanding and Intelligent Applications. ICCPOL NLPCC 2016 2016. Lecture Notes in Computer Science(), vol 10102. Springer, Cham. https://doi.org/10.1007/978-3-319-50496-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-50496-4_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50495-7
Online ISBN: 978-3-319-50496-4
eBook Packages: Computer ScienceComputer Science (R0)