Abstract
Most existing studies construct a discourse structure tree following two popular methods: top-down or bottom-up strategy. However, they often suffered from cascading errors because they can not switch the strategy of building a structure tree to avoid mistakes caused by uncertain decision-making. Moreover, due to the different basis of top-down and bottom-up methods in building discourse trees, thoroughly combining the advantages of the two methods is challenging. To alleviate these issues, we propose a Bidirectional macro-level dIscourse Parser based on OracLe selEction (BIPOLE), which combines the top-down and bottom-up strategies by selecting the suitable decision-making strategy. BIPOLE consists of a basic parsing module composed of top-down and bottom-up sub-parsers and a decision-maker for selecting a prediction strategy by considering each sub-parser state. Moreover, we propose a label-based data-enhanced oracle training strategy to generate the training data of the decision-maker. Experimental results on MCDTB and RST-DT show that our model can effectively alleviate cascading errors and outperforms the SOTA baselines significantly.
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
References
Liakata, M., Dobnik, S., Saha, S., Batchelor, C., Schuhmann, D.R.: A discourse-driven content model for summarising scientific articles evaluated in a complex question answering task. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 747–757 (2013)
Meyer, T., Popescu-Belis, A.: Using sense-labeled discourse connectives for statistical machine translation. In: Proceedings of the EACL2012 Workshop on Hybrid Approaches to Machine Translation (HyTra), no. CONF (2012)
Cohan, A., Goharian, N.: Scientific article summarization using citation-context and article’s discourse structure, arXiv preprint arXiv:1704.06619 (2017)
Presutti, V., Draicchio, F., Gangemi, A.: Knowledge extraction based on discourse representation theory and linguistic frames. In: ten Teije, A., Völker, J., Handschuh, S., Stuckenschmidt, H., d’Acquin, M., Nikolov, A., Aussenac-Gilles, N., Hernandez, N. (eds.) EKAW 2012. LNCS (LNAI), vol. 7603, pp. 114–129. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33876-2_12
Jiang, F., Xu, S., Chu, X., Li, P., Zhu, Q., Zhou, G.: Mcdtb: a macro-level chinese discourse treebank. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 3493–3504 (2018)
Fan, Y., Jiang, F., Chu, X., Li, P., Zhu, Q.: Combining global and local information to recognize chinese macro discourse structure. In: Proceedings of the 19th Chinese National Conference on Computational Linguistics, pp. 183–194 (2020)
Liu, L., Lin, X., Joty, S., Han, S., Bing, L.: Hierarchical pointer net parsing, arXiv preprint arXiv:1908.11571 (2019)
Lin, X., Joty, S., Jwalapuram, P., Bari, M.S.: A unified linear-time framework for sentence-level discourse parsing, arXiv preprint arXiv:1905.05682 (2019)
Koto, F., Lau, J.H., Baldwin, T.: Top-down discourse parsing via sequence labelling, arXiv preprint arXiv:2102.02080 (2021)
Zhou, Y., Chu, X., Li, P., Zhu, Q.: Constructing chinese macro discourse tree via multiple views and word pair similarity. In: Tang, J., Kan, M.-Y., Zhao, D., Li, S., Zan, H. (eds.) NLPCC 2019. LNCS (LNAI), vol. 11838, pp. 773–786. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32233-5_60
Jiang, F., Chu, X., Li, P., Kong, F., Zhu, Q.: Chinese paragraph-level discourse parsing with global backward and local reverse reading. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 5749–5759 (2020)
Jiang, F., Fan, Y., Chu, X., Li, P., Zhu, Q., Kong, F.: Hierarchical macro discourse parsing based on topic segmentation. In: Proceedings of the Conference on Artificial Intelligence (AAAI), pp. 13152–13160 (2021)
Feng, V.W., Hirst, G.: A linear-time bottom-up discourse parser with constraints and post-editing. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 511–521 (2014)
Li, Q., Li, T., Chang, B.: Discourse parsing with attention-based hierarchical neural networks. In: EMNLP, pp. 362–371 (2016)
Hung, S.S., Huang, H.H., Chen, H.H.: A complete shift-reduce chinese discourse parser with robust dynamic oracle. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 133–138 (2020)
Zhou, J., Jiang, F., Chu, X., Li, P., Zhu, Q.: More Than One-Hot: Chinese Macro Discourse Relation Recognition on Joint Relation Embedding. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds.) ICONIP 2021. CCIS, vol. 1516, pp. 73–80. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-92307-5_9
Chen, Q., Zhang, R., Zheng, Y., Mao, .: ual contrastive learning: Text classification via label-aware data augmentation, arXiv preprint arXiv:2201.08702,(2022)
Carlson, L., Marcu, D., Okurowski, M.E. (2003). Building a Discourse-Tagged Corpus in the Framework of Rhetorical Structure Theory. In: van Kuppevelt, J., Smith, R.W. (eds) Current and New Directions in Discourse and Dialogue. Text, Speech and Language Technology, vol 22. Springer, Dordrecht. https://doi.org/10.1007/978-94-010-0019-2_5
Mabona, A., Rimell, L., Clark, S., Vlachos, A.: Neural generative rhetorical structure parsing, arXiv preprint arXiv:1909.11049 (2019)
Fried, D., Stern, M., Klein, D.: Improving neural parsing by disentangling model combination and reranking effects, arXiv preprint arXiv:1707.03058 (2017)
Zhang, L., Tan, X., Kong, F., Zhou, G.: A recursive information flow gated model for RST-style text-level discourse parsing. In: Tang, J., Kan, M.-Y., Zhao, D., Li, S., Zan, H. (eds.) NLPCC 2019. LNCS (LNAI), vol. 11839, pp. 231–241. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32236-6_20
Zhang, L., Xing, Y., Kong, F., Li, P., Zhou, G.: A top-down neural architecture towards text-level parsing of discourse rhetorical structure, arXiv preprint arXiv:2005.02680 2020
Zhang, L., Kong, F., Zhou, G.,: Adversarial learning for discourse rhetorical structure parsing. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 3946–3957 (2021)
Kobayashi, N., Hirao, T., Nakamura, K., Kamigaito, H., Okumura, M., Nagata, M.: Split or merge: Which is better for unsupervised rst parsing? In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5797–5802 (2019)
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: Generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Mann, W.C., Thompson, S.A.: Rhetorical structure theory: toward a functional theory of text organization. Text-Interdiscp. J. Study Discourse 8(3), 243–281 (1988)
Zhang, Y., Kamigaito, H., Okumura, M.: A language model-based generative classifier for sentence-level discourse parsing. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 2432–2446 (2021)
Fan, Y., Jiang, F., Chu, X., Li, P., Zhu, Q.: Chinese macro discourse parsing on dependency graph convolutional network. In: Wang, L., Feng, Y., Hong, Yu., He, R. (eds.) NLPCC 2021. LNCS (LNAI), vol. 13028, pp. 15–26. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-88480-2_2
Chu, X., Xi, X., Jiang, F., Xu, S., Zhu, Q., Zhou, G.: Macro discourse structure representation schema and corpus construction. J. Softw. 31(2), 321–343 (2020)
Khosla, P., et al.: In: Supervised contrastive learning, In: Advances in Neural Information Processing Systems, vol. 33, pp. 18 661–18 673 (2020)
Acknowledgments
The authors would like to thank the three anonymous reviewers for their comments on this paper. This research was supported by the National Natural Science Foundation of China (Nos. 61836007, and 62006167.), and the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
He, L. et al. (2022). Bidirectional Macro-level Discourse Parser Based on Oracle Selection. In: Khanna, S., Cao, J., Bai, Q., Xu, G. (eds) PRICAI 2022: Trends in Artificial Intelligence. PRICAI 2022. Lecture Notes in Computer Science, vol 13630. Springer, Cham. https://doi.org/10.1007/978-3-031-20865-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-20865-2_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20864-5
Online ISBN: 978-3-031-20865-2
eBook Packages: Computer ScienceComputer Science (R0)