Abstract
Discourse structure recognition is an important aspect of the discourse structure rationality research. However, the assessment of discourse structure recognition usually suffer from the problems such as poor theory and lack of professional Chinese discourse structure corpus. We propose a discourse structure recognition model that consisted by the feature extraction method of “part-of-speech ratio & variance & Doc2vec” and three text classification methods that are Conditional Random Field (CRF), Support Vector Machine (SVM) and Naive Bayes for identifying discourse structure composition. We did two experiments to test the precision of the model and the highest precision reached 70.01%. What’s more, we did an experiment to study the effects of five types of paragraph labels on the model and the highest precision reached 82.13%. All experiments uses our own composition corpus of primary and secondary school students. Experimental results on datasets demonstrate that our model can be feasible and effective on research on discourse structure composition.
Supported by Key Special Projects of National Key R&D Program of China (2018YFC0830100), National Natural Science Foundation of China (61672361), and Beijing Municipal Education Commission-Beijing Natural Fund Joint Funding Project (KZ201910028039).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ltp Cloud Homepage. http://www.ltp-cloud.com/. Accessed 8 Jan 2019
Changhuo, X., Dong, C.: A preliminary study on the automatic scoring of Chinese as a second language composition. International Chinese Teaching and Research (2015). (in Chinese)
Chen, Y.: The status quo and prospect of automatic scoring of composition. Language Teaching in Middle School (2012). (in Chinese)
Xu, F., Zhu, Q., Zhou, G., Wang, M.: Cohesion-driven discourse coherence modeling. J. Chin. Inf. Process. 28, 11–21 (2014). (in Chinese)
Li, G., Zhang, Y., Li, R.: Discourse relation recognition based on Chinese framenet. J. Chin. Inf. Process. (2017). (in Chinese)
Lv, G., Su, N.: A study on Chinese discourse coherence based on CFN. J. Chin. Inf. Process. 31, 40–49 (2017). (in Chinese)
Sun, J., Li, Y.: Research of Chinese implicit discourse relation recognition. ACTA Scientiaurm Naturalium Universitatis Pekinensis 50, 111–117 (2014). (in Chinese)
Lau, J.H., Baldwin, T.: An empirical evaluation of doc2vec with practical insights into document embedding generation. Journal (2016)
Le, Q., Mikolov, T.: Distributed representations of sentences and documents. Journal (2014)
Li, J., Hovy, E.: A model of coherence based on distributed sentence representation. In: Proceedings of the EMNLP (2014)
Louis, A., Nenkova, A.: A coherence model based on syntactic patterns. In: Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (2012)
Mann, W.C., Thompson, S.: A relational propositions in discourse. Journal (1986)
Mikolov, T., Sutskever, I., Chen, K., et al.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems (2013)
Mikolov, T., Chen, K., Corrado, G., et al.: Efficient estimation of word representations in vector space. Computer Science (2013)
Zhang, M., Qin, B., Liu, T.: Chinese discourse relation semantic taxonomy and annotation. J. Chin. Inf. Process. 28, 28–36 (2014). (in Chinese)
Prasad, R., Dinesh, D.: The Penn discourse TreeBank 2.0. Journal (2008)
Guo, X.: Research and implementation of ICTCLAS API with Delphi. Comput. Program. Skills Maintenance (2011). (in Chinese)
Yuting, Y., Mingyang, W.: Sina microblog sentiment classification based on distributed representation of documents. J. Intell. (2016). (in Chinese)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, L., Liu, J., Han, X., Tan, X. (2019). The Discourse Structure Recognition Model Based on Text Classification. In: Tan, Y., Shi, Y., Niu, B. (eds) Advances in Swarm Intelligence. ICSI 2019. Lecture Notes in Computer Science(), vol 11656. Springer, Cham. https://doi.org/10.1007/978-3-030-26354-6_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-26354-6_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26353-9
Online ISBN: 978-3-030-26354-6
eBook Packages: Computer ScienceComputer Science (R0)