Focus-sensitive relation disambiguation for implicit discourse relation detection

Abstract

We study implicit discourse relation detection, which is one of the most challenging tasks in the field of discourse analysis. We specialize in ambiguous implicit discourse relation, which is an imperceptible linguistic phenomenon and therefore difficult to identify and eliminate. In this paper, we first create a novel task named implicit discourse relation disambiguation (IDRD). Second, we propose a focus-sensitive relation disambiguation model that affirms a truly-correct relation when it is triggered by focal sentence constituents. In addition, we specifically develop a topicdriven focus identification method and a relation search system (RSS) to support the relation disambiguation. Finally, we improve current relation detection systems by using the disambiguation model. Experiments on the penn discourse treebank (PDTB) show promising improvements.

Keywords

Implicit discourse relation / focus-sensitive implicit relation disambiguation / topic-driven focus identification

References

[1] Prasad R, Dinesh N, Lee A, Miltsakaki E, Robaldo L, Joshi A, Webber B. The penn discourse treebank 2.0. In: Proceedings of the 6th International Conference on Language Resources and Evaluation. 2008

[2] Wang W T, Su J, Tan C L. Kernel based discourse relation recognition with temporal ordering information. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. 2010, 710–719

[3] Pitler E, Nenkova A. Using syntax to disambiguate explicit discourse connective in text. In: Proceedings of the ACL-IJCNLP 2009 Conference Short Papers. Association for Computational Linguistics. 2009, 13–16

[4] Miltsakaki E, Dinesh N, Prasad R, Joshi A, Webber B. Experiments on sense annotations and sense disambiguation of discourse connectives. In: Proceedings of the 4thWorkshop on Treebanks and Linguistic Theories. 2005, 1–12

[5] Pitler E, Louis A, Nenkova A. Automatic sense prediction for implicit discourse relations in text. In: Proceedings of the Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation. 2009, 683–691

[6] Pitler E, Raghupathy M, Nenkova H M, Lee A, Joshi A. Easily identifiable discourse relations. In: Proceedings of the 22nd International Conference on Computational Linguistics. 2008, 87–90

[7] Lin Z H, Kan M Y, Ng H T. Recognizing implicit discourse relations in the penn discourse treebank. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing. 2009, 343–351

[8] Biran O, McKeown K. Aggregated word pair features for implicit discourse relation disambiguation. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. 2013, 69–73

[9] Park J, Cardie C. Improving implicit discourse relation recognition through feature set optimization. In: Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2012, 108–112

[10] Lan M, Xu Y, Niu Z Y. Leveraging synthetic discourse data via multitask learning for implicit discourse relation recognition. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. 2013, 476–485

[11] Marcu D, Echihabi A. An unsupervised approach to recognizing discourse relations. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 2002, 368–375

[12] Saito M, Yamamoto K, Sekine S. Using phrasal patterns to identify discourse relations. In: Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics. 2006, 133–136

[13] Zhou M Z, Xu Y, Niu Y Z, Lan M, Su J, Tan C L. Predicting discourse connectives for implicit discourse relation recognition. In: Proceedings of the 23rd International Conference on Computational Linguistics. 2010, 1507–1514

[14] Hong Y, Zhou X P, Che T T, Yao J M, Zhu Q M, Zhou G D. Crossargument inference for implicit discourse relation recognition. In: Proceedings of the 21st International Conference on Information and Knowledge Management. 2012, 295–304

[15] Ji Y F, Eisenstein J. One vector is not enough: entity-augmented distributed semantics for discourse relations. Transactions of the Association for Computational Linguistics, 2015, 3: 329–344

[16] Zhang B, Su J S, Xiong D Y, Lu Y J, Duan H, Yao J F. Shallow convolutional neural network for implicit discourse relation recognition. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015, 2230–2235

[17] Chen J F, Zhang Q, Liu P F, Huang X J. Discourse relations detection via a mixed generative-discriminative framework. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence. 2016, 2921–2927

[18] Liu Y, Li S J, Zhang X D, Sui Z F. Implicit discourse relation classification via multi-task neural networks. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence. 2016, 2750–2756

[19] Chen J F, Zhang Q, Liu P F, Qiu X P, Huang X J. 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. 2016, 1726–1735

[20] Akaike H. Information theory and an extension of the maximum likelihood principle. In: Proceedings of the 2nd International Symposium on Information Theory. 1973, 267–281

[21] Lambrecht K. Information Structure and Sentence Form: Toplic, Focus, and the Mental Representations of Discourse References. Cambridge: Cambridge University Press, 1978, 206–219

[22] Matsuo Y, Ishizuka M. Keyword extraction from a single document using word co-occurrence statistical information. Journal of Artificial Intelligence Tools, 2004, 13(1): 157–169

[23] Church K W, Hanks P. Word association norms, mutual information, and lexicography. In: Proceedings of the 27th Annual Meeting of the Association for Computational Linguistics. 1990, 76–83

[24] Napoles C, Gormley M, Durme B V. Annotated gigaword. In: Proceedings of the Joint Workshop on Automatic Knowledge Base Construction & Web-scale Knowledge Extraction of NAACL-HLT. 2012, 95–100

[25] Coifman R R, Wicherhauser M V. Entropy-based algorithms for best basis selection. IEEE Transactions on Information Theory, 1992, 38(2): 713–718

[26] Vapnik V N. The Nature of Statistical Learning Theory. Springer Science & Business Media, 1995

[27] Wolf F, Gibson E. Representing discourse coherence: a corpus-based analysis. In: Proceedings of the 20th International Conference on Computational Linguistics. 2005, 134–140

[28] Miltsakaki E, Robaldo L, Lee A, Joshi A. Sense annotation in the penn discourse treebank. In: Proceedings of International Conference on Intelligent Text Processing and Computational Linguistics. 2008, 275–286

RIGHTS & PERMISSIONS

2018 Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature