Abstract
Document-based question answering (DBQA) is a sub-task in question answering. It aims to measure the matching relation between questions and answers, which can be regarded as sentence matching problem. In this paper, we introduce a Compare-Aggregate architecture to handle the word-level comparison and aggregation. To deal with the noisy information in traditional attention mechanism, the k-top attention mechanism is proposed to filter out irrelevant words. Subsequently, we propose a combined model to merge matching relation learned by Compare-Aggregate model with shallow features to generate the final matching score. We evaluate our model on Chinese Document-based Question Answering (DBQA) task. The experimental results show the effectiveness of our proposed improved methods. And our final combined model achieves second place result on the DBQA task of NLPCC-ICCPOL 2017 Shared Task. The paper provides the technical details of the proposed algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
References
Bowman, S.R., Angeli, G., Potts, C., et al.: A large annotated corpus for learning natural language inference. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (2015)
Feng, M., Xiang, B., Glass, M.R., Wang, L., Zhou, B.: Applying deep learning to answer selection: a study and an open task. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 813–820. IEEE (2015)
He, H., Lin, J.: Pairwise word interaction modeling with deep neural networks for semantic similarity measurement. In: Proceedings of NAACL-HLT, pp. 937–948 (2016)
Bromley, J., Guyon, I., LeCun, Y., et al.: Signature verification using a “Siamese” time delay neural network. In: Advances in Neural Information Processing Systems, pp. 737–744 (1994)
Rao, J., He, H., Lin, J.: Noise-contrastive estimation for answer selection with deep neural networks. In: Proceedings of the CIKM, pp. 1913–1916 (2016)
Kang, L., Hu, B., Wu, X., Chen, Q., He, Y.: A short texts matching method using shallow features and deep features. In: Zong, C., Nie, J.Y., Zhao, D., Feng, Y. (eds.) NLPCC 2014. CCIS, vol. 496, pp. 150–159. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-45924-9_14
Kim, Y.: Convolutional neural networks for sentence classification. In: EMNLP (2014)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
Tan, M., dos Santos, C.N., Xiang, B., Zhou, B.: Improved representation learning for question answer matching. In: Meeting of the Association for Computational Linguistics, pp. 464–473 (2016)
Parikh, A.P., Täckström, O., Das, D., Uszkoreit, J.: A decomposable attention model for natural language inference. In: EMNLP (2016)
Wang, S., Jiang, J.: Learning natural language inference with LSTM (2015)
Wang, S., Jiang, J.: A compare-aggregate model for matching text sequences. arXiv preprint arXiv:1611.01747 (2016)
Yang, Y., Yih, W.T., Meek, C.: WikiQA: a challenge dataset for open-domain question answering. In: EMNLP, pp. 2013–2018 (2015)
Yin, W., Schütze, H.: Convolutional neural network for paraphrase identification. In: HLT-NAACL, pp. 901–911 (2015)
Yin, W., Schütze, H., Xiang, B., Zhou, B.: ABCNN: attention-based convolutional neural network for modeling sentence pairs. arXiv preprint arXiv:1512.05193 (2015)
Acknowledgments
This work is supported by Beijing Natural Science Foundation (4174098), the Fundamental Research Funds for the Central Universities (2017RC02) and the Natural Science Foundation of China under Grant No. 61671078 and 61471058. The authors are partially supported by CAS-NDST Lab under Grant No. CASNDST201701.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Wang, Z., Bian, W., Li, S., Chen, G., Lin, Z. (2018). Improved Compare-Aggregate Model for Chinese Document-Based Question Answering. In: Huang, X., Jiang, J., Zhao, D., Feng, Y., Hong, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2017. Lecture Notes in Computer Science(), vol 10619. Springer, Cham. https://doi.org/10.1007/978-3-319-73618-1_61
Download citation
DOI: https://doi.org/10.1007/978-3-319-73618-1_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-73617-4
Online ISBN: 978-3-319-73618-1
eBook Packages: Computer ScienceComputer Science (R0)