Abstract
Elementary Discourse Unit (EDU) recognition is the basic task of discourse analysis, and the Chinese and English discourse alignment corpus is helpful to the studies of EDU recognition. This paper first builds Chinese-English parallel discourse corpus, in which EDUs are annotated and aligned. Then, we present the framework of Bi-LSTM-CRF EDUs recognition model using word embedding, POS and syntactic features, which can combine the advantage of CRF and Bi-LSTM models. The results show that F1 is about 2% higher than the traditional method. Compared with CRF and Bi-LSTM, the Bi-LSTM-CRF model can combine the advantages of them and obtains satisfactory results for Chinese and English EDUs recognition. The experiment of feature contribution shows that using all features together can get best result, the syntactic feature outperforms than other features.
Supported by organization National Natural Science Foundation of China (61502149).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Braud, C., Lacroix, O., Anders, S.: Does syntax help discourse segmentation? Not so much. In: Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, pp. 2432–2442. Association for Computational Linguistics (2017)
Carlson, L., Marcu, D., Okurowski, M.E.: 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, pp. 85–112. Springer, Dordrecht (2003). https://doi.org/10.1007/978-94-010-0019-2_5
Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7), 257–269 (2011)
Elwell, R., Baldridge, J.: Discourse connective argument identification with connective specific rankers. In: IEEE International Conference on Semantic Computing, pp. 198–205 (2008)
Feng, W.H.: Alignment and annotation of Chinese-English discourse structure parallel corpus. J. Chin. Inf. Process. 27(6), 158–165 (2013)
Ge, H.Z., Kong, F., Zhou, G.D.: Chinese elementary discourse unit recognition based on theme-rheme theory. J. Chin. Inf. Process. 33(8), 20–27 (2019)
Goller, C., Kuchler, A.: Learning task-dependent distributed representations by back-propagation through structure. In: IEEE International Conference on Neural Networks, Washington, DC, USA, pp. 347–352 (1996)
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5), 602–610 (2005)
Greenberg, N., Bansal, T., Verga, P., McCallum, A.: Marginal likelihood training of BiLSTM-CRF for biomedical named entity recognition from disjoint label sets. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, pp. 2824–2829. Association for Computational Linguistics (2018)
Hernault, H., Bollegala, D., Ishizuka, M.: A sequential model for discourse segmentation. In: Gelbukh, A. (ed.) CICLing 2010. LNCS, vol. 6008, pp. 315–326. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-12116-6_26
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. Computation and Language (2015)
Ji, M., Kuzman, G., David, W: State-of-the-art Chinese word recognition with Bi-LSTMs. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Melbourne, Australia, pp. 4902–4908. Association for Computational Linguistics (2018)
Lafferty, J., Mccallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning, pp. 282–289. Morgan Kaufmann Publishers Inc (2001)
Li, S., Zhao, Z., Hu, R., et al.: Analogical reasoning on Chinese morphological and semantic relations. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, pp. 138–143. Association for Computational Linguistics (2018)
Li, Y.C., Feng, W.H., Sun, J., et al.: Building Chinese discourse corpus with connective-driven dependency tree structure. In: Proceedings of Empirical Methods in Natural Language Processing, Doha, Qatar, pp. 2105–2114. Association for Computational Linguistics (2014)
Li, Y.C., Feng, W.H., Zhou, G.D., et al.: Research of Chinese clause identification based on comma. Acta Scientiarum Naturalium Universitatis Pekinensis 49(1), 7–14 (2013)
Ma, X., Hovy, E.: End-to-end sequence labeling via Bi-directional LSTM-CNNs-CRF. In: Proceedings of the Meeting of the Association for Computational Linguistics, Berlin, Germany, pp. 1064–1074. Association for Computational Linguistics (2016)
Manning, C.D., Mihai, S., John, B., et al.: The stanford core NLP natural language processing toolkit. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, Maryland, pp. 55–60. Association for Computational Linguistics (2014)
Mikolov, T., Sutskever, I., Chen, K., et al.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems 26, pp. 3111–3119 (2013)
PDTB Research Group. The Penn discourse Treebank 2.0 annotation manual. IRCS Technical Reports Series (2007)
Prasad, R., Joshi, A.K., Webber, B.L.: Exploiting scope for shallow discourse parsing. In: Proceedings of the Seventh International Conference on Language Resources and their Evaluation, Valletta, Malta, pp. 2076–2083 (2010)
Soricut, R., Marcus, D.: Sentence level discourse parsing using syntactic and lexical information. In: Proceedings of the 2003 Conference of the North American, pp. 149–156 (2003)
Wellner, B., Pustejovsky, J.: Automatically identifying the arguments of discourse connectives. In: EMNLP-CoNLL, Prague, Czech Republic, pp. 92–101. Association for Computational Linguistics (2007)
Srivastava, N., Hinton, G., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Wellner, B.: Sequence models and ranking methods for discourse parsing. Faculty of the Graduate School of Arts and Sciences Brandeis University Computer Science James Pustejovsky, Brandeis University (2009)
Xu, F.: Research of key issues in english discourse structure analysis. Soochow University (2013)
Zhang, M.Y., Qin, B., Liu, T.: Chinese discourse relation semantic taxonomy and annotation. J. Chin. Inf. Process. 28(2), 28–36 (2014)
Acknowledgements
This paper is supported by the National Natural Science Foundation of China (61502149), by the Open Research Fund of Key Laboratory of Advanced Theory and Application in Statistics and Data Science (East China Normal University), Ministry of Education (KLATASDS1806), as well as the high-level talent research project of Henan Institute of Science and Technology (2017039).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Y., Lai, C., Feng, J., Feng, H. (2020). Chinese and English Elementary Discourse Units Recognition Based on Bi-LSTM-CRF Model. In: Sun, M., Li, S., Zhang, Y., Liu, Y., He, S., Rao, G. (eds) Chinese Computational Linguistics. CCL 2020. Lecture Notes in Computer Science(), vol 12522. Springer, Cham. https://doi.org/10.1007/978-3-030-63031-7_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-63031-7_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63030-0
Online ISBN: 978-3-030-63031-7
eBook Packages: Computer ScienceComputer Science (R0)