Recognizing Macro Chinese Discourse Structure on Label Degeneracy Combination Model

  • Feng Jiang
  • Peifeng LiEmail author
  • Xiaomin Chu
  • Qiaoming Zhu
  • Guodong Zhou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11109)


Discourse structure analysis is an important task in Natural Language Processing (NLP) and it is helpful to many NLP tasks, such as automatic summarization and information extraction. However, there are only a few researches on Chinese macro discourse structure analysis due to the lack of annotated corpora. In this paper, combining structure recognition with nuclearity recognition, we propose a Label Degeneracy Combination Model (LD-CM) to find the solution of structure recognition in the solution space of nuclearity recognition. Experimental results on the Macro Chinese Discourse TreeBank (MCDTB) show that our model improves the accuracy by 1.21%, compared with the baseline system.


Label degeneracy Combination model Macro discourse structure 



The authors would like to thank three anonymous reviewers for their comments on this paper. This research was supported by the National Natural Science Foundation of China under Grant Nos. 61772354, 61773276 and 61472265, and was also supported by the Strategic Pioneer Research Projects of Defense Science and Technology under Grant No. 17-ZLXDXX-02-06-02-04.


  1. 1.
    Li, Y.: Research on the structure of Chinese text structure and the construction of resources. Soochow University (2015)Google Scholar
  2. 2.
    Van Dijk, T.A.: Narrative macro-structures. PTL J. Descr. Poet. Theory Lit. 1, 547–568 (1976)Google Scholar
  3. 3.
    Hernault, H., Prendinger, H., duVerle, D.A., Ishizuka, M.: HILDA: a discourse parser using support vector machine classification. Dialogue Discourse 1(3), 1–33 (2010)CrossRefGoogle Scholar
  4. 4.
    Joty, S., Carenini, G., Ng, R., Mehdad, Y.: Combining intra- and multi-sentential rhetorical parsing for document-level discourse analysis. In: ACL 2013, vol. 1, pp. 486–496. ACL, Sofia (2013)Google Scholar
  5. 5.
    Feng, V.W., Hirst, G.: A linear-time bottom-up discourse parser with constraints and post-editing. In: ACL 2014, pp. 511–521. ACL, Baltimore (2014)Google Scholar
  6. 6.
    Li, J., Li, R., Hovy, E.: Recursive deep models for discourse parsing. In: EMNLP 2014, pp. 2061–2069. ACL, Doha (2014)Google Scholar
  7. 7.
    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. ACL, Austin (2016)Google Scholar
  8. 8.
    Sagae, K.: Analysis of discourse structure with syntactic dependencies and data-driven shift-reduce parsing. In: International Workshop on Parsing Technologies, pp. 81–84. ACL, Paris (2009)Google Scholar
  9. 9.
    Feng, V.W., Hirst, G.: Text-level discourse parsing with rich linguistic features. In: ACL 2012, vol. 1, pp. 60–68. ACL, Jeju (2012)Google Scholar
  10. 10.
    Wang, Y., Li, S., Wang, H.: A two-stage parsing method for text-level discourse analysis. In: ACL 2017, vol. 2, pp. 184–188. ACL, Vancouver (2017)Google Scholar
  11. 11.
    Lv, G., Na, S., Li, R., Wang, Z., Chai, Q.: Frame-based discourse structure modeling and relation recognition for Chinese sentence. J. Chin. Inf. Process. 29(6), 98–109 (2015)Google Scholar
  12. 12.
    Sporleder, C., Lascarides, A.: Combining hierarchical clustering and machine learning to predict high-level discourse structure. In: Coling 2004, pp. 43–49. ACM, Geneva (2004)Google Scholar
  13. 13.
    Jiang, F., Chu, X., Sheng, X., Li, P., Zhu, Q.: A macro discourse primary and secondary relation recognition method. J. Chin. Inf. Process. 32(1), 43–50 (2018)Google Scholar
  14. 14.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. Comput. Sci. (2013)Google Scholar
  15. 15.
    Xu, S.: Research and Implementation of Paraphrase Recognition for Question Answering. Harbin Institute of Technology (2009)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Feng Jiang
    • 1
  • Peifeng Li
    • 1
    Email author
  • Xiaomin Chu
    • 1
  • Qiaoming Zhu
    • 1
  • Guodong Zhou
    • 1
  1. 1.School of Computer Science and TechnologySoochow UniversitySuzhouChina

Personalised recommendations