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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
PDTB contains only 16,053 implicit discourse relation instances.
References
Biran, O., McKeown, K.: Aggregated word pair features for implicit discourse relation disambiguation. In: Proceedings of ACL Conference, p. 69 (2013)
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)
Braud, C., Denis, P.: Comparing word representations for implicit discourse relation classification. In: EMNLP 2015 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv preprint arXiv:1502.03167
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
Klein, D., Manning, C.D.: Accurate unlexicalized parsing. In: Proceedings of ACL 2003, pp. 423–430 (2003)
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)
Lin, Z., Kan, M.Y., Ng, H.T.: Recognizing implicit discourse relations in the Penn Discourse Treebank. In: Proceedings of EMNLP 2009 (2009)
Liu, Y., Li, S., Zhang, X., Sui, Z.: Implicit discourse relation classification via multi-task neural networks (2016). arXiv preprint arXiv:1603.02776
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)
Marcu, D., Echihabi, A.: An unsupervised approach to recognizing discourse relations. In: Proceedings of ACL 2002, pp. 368–375. Association for Computational Linguistics (2002)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). arXiv preprint arXiv:1301.3781
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)
Pei, W., Ge, T., Baobao, C.: Maxmargin tensor neural network for Chinese word segmentation. In: Proceedings of ACL (2014)
Pitler, E., Louis, A., Nenkova, A.: Automatic sense prediction for implicit discourse relations in text. In: Proceedings of ACL 2009 (2009)
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)
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
Rutherford, A.T., Demberg, V., Xue, N.: Neural network models for implicit discourse relation classification in English and Chinese without surface features (2016)
Rutherford, A.T., Xue, N.: Discovering implicit discourse relations through brown cluster pair representation and coreference patterns. In: EACL 2014, p. 645 (2014)
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)
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)
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)
Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: ICML, vol. 97, pp. 412–420 (1997)
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)
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)
Acknowledgments
The research work has been funded by the Natural Science Foundation of China under Grant No. 61403379.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights 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)