Skip to main content
SpringerLink
Log in

Predicting Implicit Discourse Relation with Multi-view Modeling and Effective Representation Learning

  • Conference paper
  • First Online:
Natural Language Understanding and Intelligent Applications (ICCPOL 2016, NLPCC 2016)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10102))

Abstract

Discourse relations between two text segments play an important role in many natural language processing (NLP) tasks. The connectives strongly indicate the sense of discourse relations, while in fact, there are no connectives in a large proportion of discourse relations, i.e., implicit discourse relations. The key for implicit relation prediction is to correctly model the semantics of the two discourse arguments as well as the contextual interaction between them. To achieve this goal, we propose a multi-view framework that consists of two hierarchies. The first one is the model hierarchy and we propose a neural network based method considering different views. The second one is the feature hierarchy and we learn multi-level distributed representations. We have conducted experiments on the standard benchmark dataset and the results show that compared with several methods our proposed method can achieve the best performance in most cases.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://code.google.com/p/word2vec/.

  2. 2.

    PDTB contains only 16,053 implicit discourse relation instances.

References

  1. Biran, O., McKeown, K.: Aggregated word pair features for implicit discourse relation disambiguation. In: Proceedings of ACL Conference, p. 69 (2013)

    Google Scholar 

  2. Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems, pp. 2787–2795 (2013)

    Google Scholar 

  3. Braud, C., Denis, P.: Comparing word representations for implicit discourse relation classification. In: EMNLP 2015 (2015)

    Google Scholar 

  4. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv preprint arXiv:1502.03167

  5. Ji, Y., Eisenstein, J.: One vector is not enough: entity-augmented distributed semantics for discourse relations. Trans. Assoc. Comput. Linguist. 3(1), 329–344 (2015). http://aclweb.org/anthology/Q15-1024

    Google Scholar 

  6. Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: Proceedings of ACL 2003, pp. 423–430 (2003)

    Google Scholar 

  7. Li, J.J., Nenkova, A.: Reducing sparsity improves the recognition of implicit discourse relations. In: 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, p. 199 (2014)

    Google Scholar 

  8. Lin, Z., Kan, M.Y., Ng, H.T.: Recognizing implicit discourse relations in the Penn Discourse Treebank. In: Proceedings of EMNLP 2009 (2009)

    Google Scholar 

  9. Liu, Y., Li, S., Zhang, X., Sui, Z.: Implicit discourse relation classification via multi-task neural networks (2016). arXiv preprint arXiv:1603.02776

  10. Louis, A., Joshi, A., Prasad, R., Nenkova, A.: Using entity features to classify implicit discourse relations. In: Proceedings of 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 59–62 (2010)

    Google Scholar 

  11. Marcu, D., Echihabi, A.: An unsupervised approach to recognizing discourse relations. In: Proceedings of ACL 2002, pp. 368–375. Association for Computational Linguistics (2002)

    Google Scholar 

  12. Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). arXiv preprint arXiv:1301.3781

  13. Park, J., Cardie, C.: Improving implicit discourse relation recognition through feature set optimization. In: Proceedings of 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue (2012)

    Google Scholar 

  14. Pei, W., Ge, T., Baobao, C.: Maxmargin tensor neural network for Chinese word segmentation. In: Proceedings of ACL (2014)

    Google Scholar 

  15. Pitler, E., Louis, A., Nenkova, A.: Automatic sense prediction for implicit discourse relations in text. In: Proceedings of ACL 2009 (2009)

    Google Scholar 

  16. Prasad, R., Lee, A., Miltsakaki, E., Robaldo, L., Joshi, A.K., Webber, B.L., Dinesh, N.: The Penn Discourse Treebank 2.0. In: LREC 2008, pp. 2961–2968 (2008)

    Google Scholar 

  17. Rutherford, A., Xue, N.: Improving the inference of implicit discourse relations via classifying explicit discourse connectives. In: Proceedings of NAACL 2015, pp. 799–808. Association for Computational Linguistics (2015). http://aclweb.org/anthology/N15-1081

  18. Rutherford, A.T., Demberg, V., Xue, N.: Neural network models for implicit discourse relation classification in English and Chinese without surface features (2016)

    Google Scholar 

  19. Rutherford, A.T., Xue, N.: Discovering implicit discourse relations through brown cluster pair representation and coreference patterns. In: EACL 2014, p. 645 (2014)

    Google Scholar 

  20. Socher, R., Chen, D., Manning, C.D., Ng, A.: Reasoning with neural tensor networks for knowledge base completion. In: Advances in Neural Information Processing Systems, pp. 926–934 (2013)

    Google Scholar 

  21. Tang, W., Zhang, L., Linninger, A.A., Tranter, R.S., Brezinsky, K.: Solving kinetic inversion problems via a physically bounded Gauss-Newton (PGN) method. Ind. Eng. Chem. Res. 44(10), 3626–3637 (2005)

    Article  Google Scholar 

  22. Xu, Y., Lan, M., Lu, Y., Niu, Z.Y., Tan, C.L.: Connective prediction using machine learning for implicit discourse relation classification. In: The 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2012)

    Google Scholar 

  23. Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: ICML, vol. 97, pp. 412–420 (1997)

    Google Scholar 

  24. Zhang, B., Su, J., Xiong, D., Lu, Y., Duan, H., Yao, J.: Shallow convolutional neural network for implicit discourse relation recognition. In: Proceedings of EMNLP 2015 (2015)

    Google Scholar 

  25. Zhou, Z.M., Xu, Y., Niu, Z.Y., Lan, M., Su, J., Tan, C.L.: Predicting discourse connectives for implicit discourse relation recognition. In: Proceedings of 23rd International Conference on Computational Linguistics: Posters, pp. 1507–1514. Association for Computational Linguistics (2010)

    Google Scholar 

Download references

Acknowledgments

The research work has been funded by the Natural Science Foundation of China under Grant No. 61403379.

Author information

Authors and Affiliations

  1. National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing, China

    Haoran Li, Jiajun Zhang, Yu Zhou & Chengqing Zong

  2. University of Chinese Academy of Sciences, Beijing, China

    Haoran Li, Jiajun Zhang, Yu Zhou & Chengqing Zong

Authors
  1. Haoran Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jiajun Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yu Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chengqing Zong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chengqing Zong .

Editor information

Editors and Affiliations

  1. Microsoft Research Asia, Beijing, China

    Chin-Yew Lin

  2. Brandeis University, Waltham, Massachusetts, USA

    Nianwen Xue

  3. Peking University, Beijing, China

    Dongyan Zhao

  4. Fudan University, Shanghai, China

    Xuanjing Huang

  5. Peking University, Beijing, China

    Yansong Feng

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing AG

About this paper

Cite this paper

Li, H., Zhang, J., Zhou, Y., Zong, C. (2016). Predicting Implicit Discourse Relation with Multi-view Modeling and Effective Representation Learning. In: Lin, CY., Xue, N., Zhao, D., Huang, X., Feng, Y. (eds) Natural Language Understanding and Intelligent Applications. ICCPOL NLPCC 2016 2016. Lecture Notes in Computer Science(), vol 10102. Springer, Cham. https://doi.org/10.1007/978-3-319-50496-4_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-50496-4_31

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-50495-7

  • Online ISBN: 978-3-319-50496-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation