Abstract
Discourse parsing aims to comprehend the structure and semantics of a document. Some previous studies have taken multiple levels of granularity methods to parse documents while disregarding the connection between granularity levels. Additionally, almost all the Chinese discourse parsing approaches concentrated on a single granularity due to lacking annotated corpora. To address the above issues, we propose a unified document-level Chinese discourse parser based on multi-granularity levels, which leverages granularity connections between paragraphs and Elementary Discourse Units (EDUs) in a document. Specifically, we first identify EDU-level discourse trees and then introduce a structural encoding module to capture EDU-level structural and semantic information. It can significantly promote the construction of paragraph-level discourse trees. Moreover, we construct the Unified Chinese Discourse TreeBank (UCDTB), which includes 467 articles with annotations from clauses to the whole article, filling the gap in existing unified corpus resources on Chinese discourse parsing. The experiments on both Chinese UCDTB and English RST-DT show that our model outperforms the SOTA baselines.
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
Notes
- 1.
We tried to embed the relationship in, but it did not work well.
- 2.
In practice we use one pair of structure labels \(\left\langle unused1\right\rangle \) and \(\left\langle unused2\right\rangle \) to represent the left and right brackets.
- 3.
In practice we use three pairs of labels \(\left\langle unused1\right\rangle \) and \(\left\langle unused2\right\rangle \), \(\left\langle unused3\right\rangle \) and \(\left\langle unused4\right\rangle \), \(\left\langle unused5\right\rangle \) and \(\left\langle unused6\right\rangle \) to correspond to the three pairs of tags \((_N\) and \()_S\), \((_S\) and \()_N\), \((_N\) and \()_N\).
- 4.
Same as the structural encoding module, we encode by using XLNet-base.
References
Sadek, J., Meziane, F.: A discourse-based approach for Arabic question answering. In: ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), vol. 16, no. 2, pp. 1–18 (2016)
Peldszus, A., Stede, M.: Joint prediction in MST-style discourse parsing for argumentation mining. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 938–948 (2015)
Bhatia, P., Ji, Y., Eisenstein, J.: Better document-level sentiment analysis from RST discourse parsing. arXiv preprint arXiv:1509.01599 (2015)
Mann, W.C., Thompson, S.A.: Rhetorical Structure Theory: A Theory of Text Organization. University of Southern California, Information Sciences Institute Los Angeles (1987)
Li, Y., Feng, W., Sun, J., Kong, F., Zhou, G.: Building Chinese discourse corpus with connective-driven dependency tree structure. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 2105–2114 (2014)
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)
Carlson, L., Marcu, D., Okurowski, M.E.: Building a discourse-tagged corpus in the framework of rhetorical structure theory. In: Current and New Directions in Discourse and Dialogue, pp. 85–112. Springer, Dordrecht (2003). https://doi.org/10.1007/978-94-010-0019-2_5
Wang, Y., Li, S., Wang, H.: A two-stage parsing method for text-level discourse analysis. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 184–188 (2017)
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)
Feng, V.W., Hirst, G.: Text-level discourse parsing with rich linguistic features. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 60–68 (2012)
Joty, S., Carenini, G., Ng, R., Mehdad, Y.: Combining intra-and multi-sentential rhetorical parsing for document-level discourse analysis. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 486–496 (2013)
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)
Kobayashi, N., Hirao, T., Kamigaito, H., Okumura, M., Nagata, M.: Top-down RST parsing utilizing granularity levels in documents. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 8099–8106 (2020)
Kong, F., Zhou, G.: A CDT-styled end-to-end Chinese discourse parser. In: ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), vol. 16, no. 4, pp. 1–17 (2017)
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 AAAI Conference on Artificial Intelligence, vol. 35, pp. 13152–13160 (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
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)
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
Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Sagae, K., Lavie, A.: A classifier-based parser with linear run-time complexity. In: Proceedings of the Ninth International Workshop on Parsing Technology, pp. 125–132 (2005)
Koto, F., Lau, J.H., Baldwin, T.: Top-down discourse parsing via sequence labelling. arXiv preprint arXiv:2102.02080 (2021)
Yu, N., Zhang, M., Fu, G., Zhang, M.: RST discourse parsing with second-stage EDU-level pre-training. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4269–4280 (2022)
Acknowledgements
The authors would like to thank the three anonymous reviewers for their comments. This research was supported by the National Natural Science Foundation of China (Nos. 61836007 and 62276177), and Project Funded by 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
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, W., Jiang, F., Fan, Y., Chu, X., Li, P., Zhu, Q. (2023). A Unified Document-Level Chinese Discourse Parser on Different Granularity Levels. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds) Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. Lecture Notes in Computer Science, vol 14187. Springer, Cham. https://doi.org/10.1007/978-3-031-41676-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-41676-7_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-41675-0
Online ISBN: 978-3-031-41676-7
eBook Packages: Computer ScienceComputer Science (R0)
