Discriminative explicit instance selection for implicit discourse relation classification

Abstract

Discourse relation classification is a fundamental task for discourse analysis, which is essential for understanding the structure and connection of texts. Implicit discourse relation classification aims to determine the relationship between adjacent sentences and is very challenging because it lacks explicit discourse connectives as linguistic cues and sufficient annotated training data. In this paper, we propose a discriminative instance selection method to construct synthetic implicit discourse relation data from easy-to-collect explicit discourse relations. An expanded instance consists of an argument pair and its sense label. We introduce the argument pair type classification task, which aims to distinguish between implicit and explicit argument pairs and select the explicit argument pairs that are most similar to natural implicit argument pairs for data expansion. We also propose a simple label-smoothing technique to assign robust sense labels for the selected argument pairs. We evaluate our method on PDTB 2.0 and PDTB 3.0. The results show that our method can consistently improve the performance of the baseline model, and achieve competitive results with the state-of-the-art models.

Graphical abstract

Keywords

discourse analysis / PDTB / discourse relation / implicit discourse relation classification / data expansion

References

[1] Webber B, Egg M, Kordoni V . Discourse structure and language technology. Natural Language Engineering, 2012, 18( 4): 437–490

[2] Hobbs J R . Coherence and coreference. Cognitive Science, 1979, 3( 1): 67–90

[3] Mann W C, Thompson S A . Rhetorical structure theory: toward a functional theory of text organization. Text-Interdisciplinary Journal for the Study of Discourse, 1988, 8( 3): 243–281

[4] 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

[5] Pitler E, Raghupathy M, Mehta H, Nenkova A, Lee A, Joshi A. Easily identifiable discourse relations. In: Proceedings of COLING 2008: Companion Volume: Posters. 2008, 87–90

[6] Kurfalı M, Östling R. Let’s be explicit about that: distant supervision for implicit discourse relation classification via connective prediction. In: Proceedings of the 1st Workshop on Understanding Implicit and Underspecified Language. 2021, 1–10

[7] 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

[8] Sporleder C, Lascarides A . Using automatically labelled examples to classify rhetorical relations: an assessment. Natural Language Engineering, 2008, 14( 3): 369–416

[9] Rutherford A, Xue N. Improving the inference of implicit discourse relations via classifying explicit discourse connectives. In: Proceedings of 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015, 799–808

[10] Ji Y, Zhang G, Eisenstein J. Closing the gap: domain adaptation from explicit to implicit discourse relations. In: Proceedings of 2015 Conference on Empirical Methods in Natural Language Processing. 2015, 2219–2224

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

[12] Kishimoto Y, Murawaki Y, Kurohashi S. Adapting BERT to implicit discourse relation classification with a focus on discourse connectives. In: Proceedings of the 12th Language Resources and Evaluation Conference. 2020, 1152–1158

[13] Song W, Liu L . Representation learning in discourse parsing: a survey. Science China Technological Sciences, 2020, 63( 10): 1921–1946

[14] Li J, Liu M, Qin B, Liu T . A survey of discourse parsing. Frontiers of Computer Science, 2022, 16( 5): 165329

[15] Xiang W, Wang B . A survey of implicit discourse relation recognition. ACM Computing Surveys, 2023, 55( 12): 258

[16] Webber B, Prasad R, Lee A, Joshi A. The Penn discourse Treebank 3.0 annotation manual. Philadelphia: University of Pennsylvania, 2019

[17] Devlin J, Chang M W, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019, 4171–4186

[18] Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V. RoBERTa: a robustly optimized BERT pretraining approach. 2019, arXiv preprint arXiv: 1907.11692

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

[20] Ji Y, Eisenstein J. Representation learning for text-level discourse parsing. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2014, 13–24

[21] Qin L, Zhang Z, Zhao H. Implicit discourse relation recognition with context-aware character-enhanced embeddings. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. 2016, 1914–1924

[22] Li H, Zhang J, Zong C . Implicit discourse relation recognition for English and Chinese with multiview modeling and effective representation learning. ACM Transactions on Asian and Low-Resource Language Information Processing, 2017, 16( 3): 19

[23] Bai H, Zhao H. Deep enhanced representation for implicit discourse relation recognition. In: Proceedings of the 27th International Conference on Computational Linguistics. 2018, 571–583

[24] Lei W, Xiang Y, Wang Y, Zhong Q, Liu M, Kan M Y. Linguistic properties matter for implicit discourse relation recognition: combining semantic interaction, topic continuity and attribution. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence and 30th Innovative Applications of Artificial Intelligence Conference and 8th AAAI Symposium on Educational Advances in Artificial Intelligence. 2018, 594

[25] Shi W, Demberg V. Next sentence prediction helps implicit discourse relation classification within and across domains. In: Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019, 5790–5796

[26] He R, Wang J, Guo F, Han Y. TransS-driven joint learning architecture for implicit discourse relation recognition. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020, 139–148

[27] Liu X, Ou J, Song Y, Jiang X. On the importance of word and sentence representation learning in implicit discourse relation classification. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence. 2021, 3830–3836

[28] Dou Z, Hong Y, Sun Y, Zhou G. CVAE-based Re-anchoring for implicit discourse relation classification. In: Proceedings of Findings of the Association for Computational Linguistics: EMNLP 2021. 2021, 1275–1283

[29] Wang X, Li S, Li J, Li W. Implicit discourse relation recognition by selecting typical training examples. In: Proceedings of COLING 2012. 2012, 2757–2772

[30] Lan M, Wang J, Wu Y, Niu Z Y, Wang H. Multi-task attention-based neural networks for implicit discourse relationship representation and identification. In: Proceedings of 2017 Conference on Empirical Methods in Natural Language Processing. 2017, 1299–1308

[31] Wu C, Shi X, Chen Y, Huang Y, Su J. Bilingually-constrained synthetic data for implicit discourse relation recognition. In: Proceedings of 2016 Conference on Empirical Methods in Natural Language Processing. 2016, 2306–2312

[32] Malmi E, Pighin D, Krause S, Kozhevnikov M. Automatic prediction of discourse connectives. In: Proceedings of the 11th International Conference on Language Resources and Evaluation. 2018

[33] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016, 2818–2826

[34] Yang Y, Zha K, Chen Y, Wang H, Katabi D. Delving into deep imbalanced regression. In: Proceedings of the 38th International Conference on Machine Learning. 2021, 11842–11851

[35] Xu Y, Hong Y, Ruan H, Yao J, Zhang M, Zhou G. Using active learning to expand training data for implicit discourse relation recognition. In: Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing. 2018, 725–731

[36] Dai Z, Huang R. A regularization approach for incorporating event knowledge and coreference relations into neural discourse parsing. In: Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019, 2976–2987

[37] Kim N, Feng S, Gunasekara C, Lastras L. Implicit discourse relation classification: we need to talk about evaluation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020, 5404–5414

[38] Liang L, Zhao Z, Webber B. Extending implicit discourse relation recognition to the PDTB-3. In: Proceedings of the 1st Workshop on Computational Approaches to Discourse. 2020, 135–147

[39] Kiyomaru H, Kurohashi S. Contextualized and generalized sentence representations by contrastive self-supervised learning: a case study on discourse relation analysis. In: Proceedings of 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021, 5578–5584

[40] He P, Liu X, Gao J, Chen W. DeBERTa: decoding-enhanced BERT with disentangled attention. In: Proceedings of the 9th International Conference on Learning Representations. 2021

RIGHTS & PERMISSIONS

Higher Education Press