Abstract
Recent works on open-domain question answering (QA) rely on retrieving related passages to answer questions. However, most of them can not escape from sub-optimal initial retrieval results because of lacking interaction with the retrieval system. This paper introduces a new framework MSReNet for open-domain question answering where the question reformulator interacts with the term-based retrieval system, which can improve retrieval precision and QA performance. Specifically, we enhance the open-domain QA model with an additional multi-step reformulator which generates a new human-readable question with the current passages and question. The interaction continues for several times before answer extraction to find the optimal retrieval results as much as possible. Experiments show MSReNet gains performance improvements on several datasets such as TriviaQA-unfiltered, Quasar-T, SearchQA, and SQuAD-open. We also find that the intermediate reformulation results provide interpretability for the reasoning process of the model.
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
Buck, C., et al.: Ask the right questions: active question reformulation with reinforcement learning. arXiv preprint arXiv:1705.07830 (2017)
Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051 (2017)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
Clark, C., Gardner, M.: Simple and effective multi-paragraph reading comprehension. arXiv preprint arXiv:1710.10723 (2017)
Das, R., Dhuliawala, S., Zaheer, M., McCallum, A.: Multi-step retriever-reader interaction for scalable open-domain question answering. arXiv preprint arXiv:1905.05733 (2019)
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)
Dhingra, B., Mazaitis, K., Cohen, W.W.: Quasar: datasets for question answering by search and reading. arXiv preprint arXiv:1707.03904 (2017)
Dunn, M., Sagun, L., Higgins, M., Guney, V.U., Cirik, V., Cho, K.: SearchQA: a new Q&A dataset augmented with context from a search engine. arXiv preprint arXiv:1704.05179 (2017)
Htut, P.M., Bowman, S.R., Cho, K.: Training a ranking function for open-domain question answering. arXiv preprint arXiv:1804.04264 (2018)
Hu, M., Peng, Y., Huang, Z., Li, D.: Retrieve, read, rerank: towards end-to-end multi-document reading comprehension. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp. 2285–2295. Association for Computational Linguistics, July 2019. https://doi.org/10.18653/v1/P19-1221, https://www.aclweb.org/anthology/P19-1221
Joshi, M., Choi, E., Weld, D.S., Zettlemoyer, L.: TriviaQA: a large scale distantly supervised challenge dataset for reading comprehension. arXiv preprint arXiv:1705.03551 (2017)
Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1–2), 99–134 (1998)
Lavrenko, V., Croft, W.B.: Relevance-based language models. In: ACM SIGIR Forum, vol. 51, pp. 260–267. ACM, New York (2017)
Lee, J., Yun, S., Kim, H., Ko, M., Kang, J.: Ranking paragraphs for improving answer recall in open-domain question answering. arXiv preprint arXiv:1810.00494 (2018)
Lee, K., Chang, M.W., Toutanova, K.: Latent retrieval for weakly supervised open domain question answering. arXiv preprint arXiv:1906.00300 (2019)
Lin, Y., Ji, H., Liu, Z., Sun, M.: Denoising distantly supervised open-domain question answering. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1736–1745 (2018)
Loshchilov, I., Hutter, F.: Fixing weight decay regularization in Adam (2018)
Nie, Y., Chen, H., Bansal, M.: Combining fact extraction and verification with neural semantic matching networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6859–6866 (2019)
Nogueira, R., Cho, K.: Task-oriented query reformulation with reinforcement learning. arXiv preprint arXiv:1704.04572 (2017)
Pang, L., Lan, Y., Guo, J., Xu, J., Su, L., Cheng, X.: Has-QA: hierarchical answer spans model for open-domain question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6875–6882, June 2019. https://doi.org/10.1609/aaai.v33i01.33016875
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Seo, M., Lee, J., Kwiatkowski, T., Parikh, A.P., Farhadi, A., Hajishirzi, H.: Real-time open-domain question answering with dense-sparse phrase index. arXiv preprint arXiv:1906.05807 (2019)
Sutskever, I.: Training recurrent neural networks. University of Toronto Toronto, Ontario, Canada (2013)
Wang, S., et al.: R3: reinforced ranker-reader for open-domain question answering. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Wang, S., et al.: Evidence aggregation for answer re-ranking in open-domain question answering. arXiv preprint arXiv:1711.05116 (2017)
Wang, Z., Ng, P., Ma, X., Nallapati, R., Xiang, B.: Multi-passage Bert: a globally normalized bert model for open-domain question answering. arXiv preprint arXiv:1908.08167 (2019)
Xu, J., Croft, W.B.: Quary expansion using local and global document analysis. In: ACM SIGIR Forum, vol. 51, pp. 168–175. ACM, New York (2017)
Yang, W., et al.: End-to-end open-domain question answering with BERTserini. arXiv preprint arXiv:1902.01718 (2019)
Acknowledgement
We thanks anonymous reviewers for their precious comments. This research is supported by the National Key R&D Program of China (Grant No. 2018YFC1604000 and No. 2018YFC1604003) and Natural Science Foundation of China (NSFC) (Grant No. 71950002 and No. 61772382).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Han, W., Peng, M., Xie, Q., Zhang, X., Wang, H. (2020). MSReNet: Multi-step Reformulation for Open-Domain Question Answering. In: Zhu, X., Zhang, M., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2020. Lecture Notes in Computer Science(), vol 12431. Springer, Cham. https://doi.org/10.1007/978-3-030-60457-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-60457-8_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60456-1
Online ISBN: 978-3-030-60457-8
eBook Packages: Computer ScienceComputer Science (R0)
