Abstract
In the e-commerce websites, such as Taobao and Amazon, interactive question-answering (QA) style reviews usually carry rich aspect information of products. To well automatically analyze the aspect information inside QA style reviews, it’s worthwhile to perform aspect classification on them. Unfortunately, until now, there are few papers that focus on performing aspect classification on the QA style reviews. For short, we referred to this novel task as QA aspect classification (QA-AC). In this study, we model this task as a multi-label classification problem where each QA style review is explicitly mapped to multiple aspect categories instead of only one aspect category. To solve this issue, we propose a contextualized attention-based neural network approach to capture both the contextual information and the QA matching information inside QA style reviews for the task of QA-AC. Specifically, we first propose two aggregating strategies to integrate multi-layer contextualized word embeddings of the pre-trained language representation model (i.e., BERT) so as to capture contextual information. Second, we propose a bidirectional attention layer to capture the QA matching information. Experimental results demonstrate the effectiveness of our approach to QA-AC.
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
Fan, F., Feng, Y., Zhao, D.: Multi-grained attention network for aspect-level sentiment classification. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3433–3442 (2018)
He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: Exploiting document knowledge for aspect-level sentiment classification. arXiv preprint. arXiv:1806.04346 (2018)
Wang, Y., Huang, M., Zhao, L., et al.: Attention-based LSTM for aspect-level sentiment classification. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 606–615 (2016)
Rubtsova, Y., Koshelnikov, S.: Aspect extraction from reviews using conditional random fields. In: Klinov, P., Mouromtsev, D. (eds.) KESW 2015. CCIS, vol. 518, pp. 158–167. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24543-0_12
Xu, H., Liu, B., Shu, L., Yu, P.S.: Double embeddings and CNN-based sequence labeling for aspect extraction. arXiv preprint. arXiv:1805.04601 (2018)
He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: An unsupervised neural attention model for aspect extraction. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 388–397 (2017)
Wu, H., Liu, M., Wang, J., Xie, J., Shen, C.: Question-answering aspect classification with hierarchical attention network. In: Sun, M., Liu, T., Wang, X., Liu, Z., Liu, Y. (eds.) CCL/NLP-NABD -2018. LNCS (LNAI), vol. 11221, pp. 225–237. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01716-3_19
Dai, A.M., Le, Q.V.: Semi-supervised sequence learning. In: Advances in Neural Information Processing Systems, pp. 3079–3087 (2015)
Kim, Y., Jernite, Y., Sontag, D., Rush, A.M.: Character-aware neural language models. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)
Peters, M.E., et al.: Deep contextualized word representations. arXiv preprint. arXiv:1802.05365 (2018)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018). https://s3-us-west-2.amazonaws.com/openai-assets/research-covers/languageunsupervised/language understanding paper.pdf
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint. arXiv:1810.04805 (2018)
Adhikari, A., Ram, A., Tang, R., Lin, J.: DocBERT: BERT for document classification. arXiv preprint. arXiv:1904.08398 (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint. arXiv:1412.6980 (2014)
Godbole, S., Sarawagi, S.: Discriminative methods for multi-labeled classification. In: Dai, H., Srikant, R., Zhang, C. (eds.) PAKDD 2004. LNCS (LNAI), vol. 3056, pp. 22–30. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-24775-3_5
Szymański, P., Kajdanowicz, T.: A scikit-based Python environment for performing multi-label classification. ArXiv e-prints (February 2017)
Acknowledgements
This work is supported in part by Industrial Prospective Project of Jiangsu Technology Department under Grant No. BE2017081 and the National Natural Science Foundation of China under Grant No. 61572129.
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
Wu, H., Zhang, S., Wang, J., Liu, M., Li, S. (2019). Multi-label Aspect Classification on Question-Answering Text with Contextualized Attention-Based Neural Network. In: Sun, M., Huang, X., Ji, H., Liu, Z., Liu, Y. (eds) Chinese Computational Linguistics. CCL 2019. Lecture Notes in Computer Science(), vol 11856. Springer, Cham. https://doi.org/10.1007/978-3-030-32381-3_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-32381-3_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32380-6
Online ISBN: 978-3-030-32381-3
eBook Packages: Computer ScienceComputer Science (R0)