Abstract
Recognizing Textual Entailment is a fundamental task of natural language processing, and its purpose is to recognize the inferential relationship between two sentences. With the development of deep learning and construction of relevant corpus, great progress has been made in English Textual Entailment. However, the progress in Chinese Textual Entailment is relatively rare because of the lack of large-scale annotated corpus. The Seventeenth China National Conference on Computational Linguistics (CCL 2018) first released a Chinese textual entailment dataset that including 100,000 sentence pairs, which provides support for application of deep learning model. Inspired by attention models on English, we proposed a Chinese recognizing textual entailment model based on co-attention and aggregation. This model uses co-attention to calculate the feature of relationship between two sentences, and aggregates this feature with another feature obtained from sentences. Our model achieved 93.5% accuracy on CCL2018 textual entailment dataset, which is higher than the first place in previous evaluations. Experimental results showed that recognition of contradiction relations is difficult, but our model outperforms other benchmark models. What’s more, our model can be applied to Chinese document based question answer (DBQA). The accuracy of the experiment results on the dataset of NLPCC2016 is 72.3%.
The authors were supported financially by the National Social Science Fund of China (18ZDA315), Programs for Science and Technology Development in Henan province (No. 192102210260) and the Key Scientific Research Program of Higher Education of Henan (No. 20A520038).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bowman, S.R., Angeli, G., Potts, C.: A large annotated corpus for learning natural language inference. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 632–642. ACL, Lisbon (2015)
Wang, S., Jiang, J.: Learning natural language inference with LSTM. arXiv preprint arXiv:1512.08849 (2015)
Tan, Y., Liu, Z., Lv, X.: CNN and BiLSTM based Chinese textual entailment recognition. J. Chin. Inf. Proc. 32(7), 11–19 (2018)
Chen, Q., Chen, X., Guo, X.: Multiple-to-One Chinese textual entailment for reading comprehension. J. Chin. Inf. Proc. 32(4), 87–94 (2018)
Parikh, A.P., Täckström, O., Das, D.: A decomposable attention model for natural language inference. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2249–2255. ACL, Austin (2016)
Shen, D., Wang, G., Wang, W.: Baseline needs more love: on simple word-embedding-based models and associated pooling mechanisms. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 440–450. ACL, Melbourne (2018)
Dagan, I., Glickman, O.: Probabilistic textual entailment: generic applied modeling of language variability. Learning Methods for Text Understanding and Mining, pp. 26–29 (2004)
Dagan, I., Glickman, O., Magnini, B.: The PASCAL recognizing textual entailment challenge. In: Quiñonero-Candela, J., Dagan, I., Magnini, B., d’Alché-Buc, F. (eds.) MLCW 2005. LNCS (LNAI), vol. 3944, pp. 177–190. Springer, Heidelberg (2006). https://doi.org/10.1007/11736790_9
Dagan, I., Roth, D., Sammons, M.: Recognizing textual entailment: models and applications. Synth. Lect. Hum. Lang. Technol. 6(4), 1–220 (2013)
Burger, J., Ferro, L.: Generating an entailment corpus from news headlines. In: Proceedings of the ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment, pp. 49–54. ACL, Ann Arbor (2005)
Williams, A., Nangia, N., Bowman, S.R.: A broad-coverage challenge corpus for sentence understanding through inference. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (Volume 1: Long Papers), pp. 1112–1122. ACL, New Orleans (2018)
Conneau, A., Kiela, D., Schwenk, H.: Supervised learning of universal sentence representations from natural language inference data. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 670–680. ACL, Copenhagen (2017)
Chen, Q., Zhu, X., Ling, Z.: Enhanced LSTM for natural language inference. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1657–1668. ACL, Vancouver (2017)
Tan, C., Wei, F., Wang, W.: Multiway attention networks for modeling sentence pairs. In: 27th International Joint Conference on Artificial Intelligence, pp. 4411–4417. Morgan Kaufmann, Sweden (2018)
Ghaeini, R., Hasan, S.A., Datla, V., et al.: DR-BiLSTM: dependent reading bidirectional LSTM for natural language inference. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 1460–1469. ACL, New Orleans (2018)
Kim, S., Kang, I., Kwak, N.: Semantic sentence matching with densely-connected recurrent and co-attentive information. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6586–6593. AAAI, Hawaii (2019)
Li, S., Zhao, Z., Hu, R., Li, W., Liu, T., Du, X.: analogical reasoning on chinese morphological and semantic relations. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 138–143. ACL, Melbourne (2018)
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
Liu, P., Mu, L., Zan, H. (2019). Co-attention and Aggregation Based Chinese Recognizing Textual Entailment Model. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11839. Springer, Cham. https://doi.org/10.1007/978-3-030-32236-6_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-32236-6_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32235-9
Online ISBN: 978-3-030-32236-6
eBook Packages: Computer ScienceComputer Science (R0)