Abstract
Discourse parsing has attracted more and more attention due to its importance on Natural Language Understanding. Accordingly, various neural models proposed and have achieved certain success. However, due to the scale limitation of corpus, outstanding performance still depends on additional features. Different from previous neural studies employing simple flat word level EDU (Elementary Discourse Unit) representation, we improve the performance of discourse parsing by employing cohesion information (In this paper, we regard lexical chain and coreference chain as cohesion information) enhanced EDU representation. In particular, firstly we use WordNet and a coreference resolution model to extract lexical and coreference chain respectively and automatically. Secondly, we construct EDU level graph based on the extracted chains. Finally, using Graph Attention Network, we incorporate the obtained cohesion information into EDU representation to improve discourse parsing. Experiments on RST-DT, CDTB and STAC show our proposed cohesion information enhanced EDU representation can benefit both written and dialogue discourse parsing, compared with the baseline model we duplicated.
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.
In the dialogue text, each utterance corresponds to an EDU.
- 2.
The split position between any two neighboring EDUs is called the split point.
- 3.
There will be \(n-2\) split points for n EDUs.
- 4.
A word similarity calculation method provided by WordNet, return a score between 0 and 1, denoting how similar two word senses are, based on the shortest path that connects the senses. Moreover, when there is no path between two senses, −1 will be returned.
- 5.
we use the same method to build lexical and coreference graph.
- 6.
In order to simplify the expression, the word and mention in lexical and coreference chain are collectively referred to as element.
- 7.
Following previous study, we used the version released on March 21, 2018.
References
Afantenos, S., Kow, E., Asher, N., Perret, J.: Discourse parsing for multi-party chat dialogues. Association for Computational Linguistics (ACL) (2015)
Asher, N., Hunter, J., Morey, M., Benamara, F., Afantenos, S.: Discourse structure and dialogue acts in multiparty dialogue: the STAC corpus (2016)
Asher, N., Lascarides, A.: Logics of Conversation. Peking University Press (2003)
Carlson, L., Marcu, D., Okurowski, M.E.: Building a discourse-tagged corpus in the framework of rhetorical structure theory. Association for Computational Linguistics (2001)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. Association for Computational Linguistics, Doha, Qatar, October 2014. https://doi.org/10.3115/v1/D14-1179. https://www.aclweb.org/anthology/D14-1179
Dozat, T., Manning, C.D.: Deep biaffine attention for neural dependency parsing (2016)
Fang, K., Fu, J.: Incorporating structural information for better coreference resolution. In: Twenty-Eighth International Joint Conference on Artificial Intelligence IJCAI-19 (2019)
Feng, V.W., Hirst, G.: A linear-time bottom-up discourse parser with constraints and post-editing. In: Meeting of the Association for Computational Linguistics (2014)
Ji, Y., Eisenstein, J.: Representation learning for text-level discourse parsing. In: Meeting of the Association for Computational Linguistics (2014)
Ji, Y., Smith, N.: Neural discourse structure for text categorization. arXiv preprint arXiv:1702.01829 (2017)
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 (2020)
Li, J., Li, R., Hovy, E.: Recursive deep models for discourse parsing. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 2061–2069 (2014)
Li, Q., Li, T., Chang, B.: Discourse parsing with attention-based hierarchical neural networks. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 362–371 (2016)
Li, Y., Feng, W., Jing, S., Fang, K., Zhou, G.: Building Chinese discourse corpus with connective-driven dependency tree structure. In: Conference on Empirical Methods in Natural Language Processing (2014)
Morris, J., Hirst, G.: Lexical cohesion computed by thesaural relations as an indicator of the structure of text. Comput. Linguistics (1991)
Nan, Y., Zhang, M., Fu, G.: Transition-based neural RST parsing with implicit syntax features (2018)
Perret, J., Afantenos, S., Asher, N., Morey, M.: Integer linear programming for discourse parsing. In: Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2016), pp. 99–109 (2016)
Shi, Z., Huang, M.: A deep sequential model for discourse parsing on multi-party dialogues (2018)
Sun, C., Fang, K.: A transition-based framework for Chinese discourse structure parsing. J. Chin. Inf. Process. (2018)
Takanobu, R., Huang, M., Zhao, Z., Li, F., Nie, L.: A weakly supervised method for topic segmentation and labeling in goal-oriented dialogues via reinforcement learning. In: Twenty-Seventh International Joint Conference on Artificial Intelligence IJCAI-18 (2018)
Velikovi, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks (2017)
Xu, J., Gan, Z., Cheng, Y., Liu, J.: Discourse-aware neural extractive model for text summarization (2019)
Zhang, L., Xing, Y., Kong, F., Li, P., Zhou, G.: A top-down neural architecture towards text-level parsing of discourse rhetorical structure. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
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)
Zhu, X., Runcong, M.A., Sun, L., Chen, H.: Word semantic similarity computation based on HowNet and CiLin. J. Chin. Inf. Process. (2016)
Acknowledgements
The authors would like to thank the anonymous reviewers for the helpful comments. We are very grateful to Zixin Ni for her help in Reference Resolution we used in this work. This work was supported by Project 61876118 under the National Natural Science Foundation of China and the Priority Academic Program Development of Jiangsu Higher Education Institutions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, J., Zhang, L., Kong, F. (2021). Multi-level Cohesion Information Modeling for Better Written and Dialogue Discourse Parsing. In: Wang, L., Feng, Y., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2021. Lecture Notes in Computer Science(), vol 13028. Springer, Cham. https://doi.org/10.1007/978-3-030-88480-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-88480-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88479-6
Online ISBN: 978-3-030-88480-2
eBook Packages: Computer ScienceComputer Science (R0)
