Abstract
Community Question Answering (CQA) provides platforms for users with various background to obtain information and share knowledge. In the recent years, with the rapid development of such online platforms, an enormous amount of archive data has accumulated which makes it more and more difficult for users to identify desirable answers. Therefore, answer selection becomes a very important subtask in Community Question Answering. A posted question often consists of two parts: a question subject with summarization of users’ intention, and a question body clarifying the subject with more details. Most of the existing answer selection techniques often roughly concatenate these two parts, so that they cause excessive noises besides useful information to questions, inevitably reducing the performance of answer selection approaches. In this paper, we propose AMQAN, an adaptive multi-attention question-answer network with embeddings at different levels, which makes comprehensive use of semantic information in questions and answers, and alleviates the noise issue at the same time. To evaluate our proposed approach, we implement experiments on two datasets, SemEval 2015 and SemEval 2017. Experiment results show that AMQAN outperforms all existing models on two standard CQA datasets.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Wu, W., Sun, X., Wang, H., et al.: Question condensing networks for answer selection in community question answering. In: Meeting of the Association for Computational Linguistics, pp. 1746–1755 (2018)
Yao, X., Van Durme, B., Callisonburch, C., et al.: Answer extraction as sequence tagging with tree edit distance. In: North American Chapter of the Association for Computational Linguistics, pp. 858–867 (2013)
Tran, Q.H., Tran, D.V., Vu, T., Le Nguyen, M., Pham, S.B.: JAIST: Combining multiple features for Answer Selection in Community Question Answering. In: North American Chapter of the Association for Computational Linguistics, pp. 215–219 (2015)
Joty, S., Marquez, L., Nakov, P.: Joint learning with global inference for comment classification in community question answering. In: North American Chapter of the Association for Computational Linguistics, pp. 703–713 (2016)
Nakov, P., Marquez, L., Moschitti, A., et al. SemEval-2016 task 3: community question answering. In: North American Chapter of the Association for Computational Linguistics, pp. 525–545 (2016)
Filice, S., Croce, D., Moschitti, A., et al.: KeLP at SemEval-2016 task 3: Learning semantic relations between questions and answers. In: North American Chapter of the Association for Computational Linguistics, pp. 1116–1123 (2016)
Wang, M., Smith, N.A., Mitamura, T.: What is the jeopardy model? a quasisynchronous grammar for QA. In: EMNLP-CoNLL (2007)
Heilman, M., Smith, N.A.: Tree edit models for recognizing textual etailments, paraphrases, and answers to questions. In: Proceedings of NAACL (2010)
Murdock, V., Croft, W.B.: Simple translation models for sentence retrieval in factoid question answering. In: Proceedings of the SIGIR-2004 Workshop on Information Retrieval For Question Answering (IR4QA), pp. 31–35 (2004)
Zhou, G., Cai, L., Zhao, J., et al.: Phrase-based translation model for question retrieval in community question answer archives. In: Meeting of the Association for Computational Linguistics, pp. 653–662 (2011)
Pennington, J., Socher, R., Manning, C. D., et al.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing, pp. 1532–1543 (2014)
Kim, Y., Jernite, Y., Sontag, D., et al.: Character-aware neural language models. In: National Conference on Artificial Intelligence pp. 2741–2749 (2016)
Chen, Q., Zhu, X., Ling, Z., et al.: Neural natural language inference models enhanced with external knowledge. In: Meeting of the Association for Computational Linguistics, pp. 2406–2417 (2018)
Lin, Z.: A structured self-attentive sentence embedding. In: International Conference on Learning Representations (ICLR) (2017)
Weissenborn, D., Wiese, G., Seiffe, L., et al.: Making neural QA as simple as possible but not simpler. In: Conference on Computational Natural Language Learning, pp. 271–280 (2017)
Yu, A.W.: QANet: combining local convolution with global self-attention for reading comprehension. In: International Conference on Learning Representations (ICLR) (2018)
Seo, M., Kembhavi, A., Farhadi, A., Hajishirzi, H.: Bidirectional attention flow for machine comprehension. In: International Conference on Learning Representations (ICLR) (2017)
Lu, J., Xiong, C., Parikh, D., et al.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: Computer Vision and Pattern Recognition, pp. 3242–3250 (2017)
Chen, Q., Zhu, X., Ling, Z., et al.: Enhanced LSTM for natural language inference. In: Meeting of the Association for Computational Linguistics, pp. 1657–1668 (2017)
Mou, L., Men, R., Li, G., et al.: Natural language inference by tree-based convolution and heuristic matching. In: Meeting of the Association for Computational Linguistics, pp. 130–136 (2016)
Tran, Q.H., Tran, V.D., Vu,T.T., et al.: JAIST: Combining multiple features for answer selection in community question answering. In: North American Chapter of the Association for Computational Linguistics, pp. 215–219 (2015)
Hou, Y., Tan, C., Wang, X., et al. HITSZ-ICRC: exploiting classification approach for answer selection in community question answering. In: North American Chapter of the Association for Computational Linguistics, pp. 196–202 (2015)
Joty, S.R., Barroncedeno, A., Martino, G.D., et al.: Global thread-level inference for comment classification in community question answering. In: Empirical Methods in Natural Language Processing, pp. 573–578 (2015)
Wei, W., Houfeng, W., Sujian, L.: Bidirectional gated memory networks for answer selection. In: Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data, LNAI 10565, Springer, Cham pp. 251–262 (2017)
Xiang, Y., Zhou, X., Chen, Q., et al.: Incorporating label dependency for answer quality tagging in community question answering via CNN-LSTM-CRF. In: International conference on computational linguistics, pp. 1231–1241 (2016)
Filice, S., Martino, G.D., Moschitti, A., et al.: KeLP at SemEval-2017 task 3: learning pairwise patterns in community question answering. In: Meeting of the Association for Computational Linguistics, pp. 326–333 (2017)
Feng, W., Wu, Y., Wu, W., et al.: Beihang-MSRA at semEval-2017 task 3: a ranking system with neural matching features for community question answering. In: Meeting of the Association for Computational Linguistics, pp. 280–286 (2017)
Wu, G., Sheng, Y., Lan, M., et al.: ECNU at semEval-2017 task 3: using traditional and deep learning methods to address community question answering task. In: Meeting of the Association for Computational Linguistics, pp. 365–369 (2017)
Zhang, X., Li, S., Sha, L., et al.: Attentive interactive neural networks for answer selection in community question answering. In: National Conference on Artificial Intelligence, pp. 3525–3531 (2017)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, H. et al. (2021). AMQAN: Adaptive Multi-Attention Question-Answer Networks for Answer Selection. In: Hutter, F., Kersting, K., Lijffijt, J., Valera, I. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2020. Lecture Notes in Computer Science(), vol 12459. Springer, Cham. https://doi.org/10.1007/978-3-030-67664-3_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-67664-3_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67663-6
Online ISBN: 978-3-030-67664-3
eBook Packages: Computer ScienceComputer Science (R0)