Abstract
This study focuses on multi-passage Machine Reading Comprehension (MRC) task. Prior work has shown that retriever, reader pipeline model could improve overall performance. However, the pipeline model relies heavily on retriever component since inferior retrieved documents would significantly degrade the performance. In this study, we proposed a new multi-perspective answer reranking technique that considers all documents to verify the confidence of candidate answers; such nuanced technique can carefully distinguish candidate answers to improve performance. Specifically, we rearrange the order of traditional pipeline model and make a posterior answer reranking instead of prior passage reranking. In addition, new proposed pre-trained language model BERT is also introduced here. Experiments with Chinese multi-passage dataset DuReader show that our model achieves competitive performance.
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
References
Yang, A., et al.: Adaptations of ROUGE and BLEU to better evaluate machine reading comprehension task. arXiv preprint arXiv:1806.03578 (2018)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)
Tan, C., et al.: S-Net: from answer extraction to answer generation for machine reading comprehension. arXiv preprint arXiv:1706.04815 (2017)
Clark, C., Gardner, M.: Simple and effective multi-paragraph reading comprehension. arXiv preprint arXiv:1710.10723 (2017)
Hill, F., et al.: The goldilocks principle: reading children’s books with explicit memory representations. arXiv preprint arXiv:1511.02301 (2015)
Devlin, J., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Liu, J., et al.: A multi-answer multi-task framework for real-world machine reading comprehension. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2109–2118 (2018)
Hermann, K.M., et al.: Teaching machines to read and comprehend. In: Advances in Neural Information Processing Systems (2015)
Nishida, K., et al.: Multi-style generative reading comprehension. arXiv preprint arXiv:1901.02262 (2019)
Nishida, K., et al.: Retrieve-and-read: multi-task learning of information retrieval and reading comprehension. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ACM (2018)
Joshi, M., et al.: TriviaQA: a large scale distantly supervised challenge dataset for reading comprehension. arXiv preprint arXiv:1705.03551 (2017)
Dunn, M., et al.: SearchQA: a new Q&A dataset augmented with context from a search engine. arXiv preprint arXiv:1704.05179 (2017)
Seo, M., et al.: Bidirectional attention flow for machine comprehension. arXiv preprint arXiv:1611.01603 (2016)
Yan, M., et al.: A deep cascade model for multi-document reading comprehension. arXiv preprint arXiv:1811.11374 (2018)
Rajpurkar, P., et al.: SQuAD: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)
Rajpurkar, P., Jia, R., Liang, P.: Know what you don’t know: unanswerable questions for SQuAD. arXiv preprint arXiv:1806.03822 (2018)
Nguyen, T., et al.: MS MARCO: a human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268 (2016)
He, W., et al.: DuReader: a Chinese machine reading comprehension dataset from real-world applications. In: Proceedings of the Workshop on Machine Reading for Question Answering (2018)
Yang, W., et al.: End-to-end open-domain question answering with BERTserini. arXiv preprint arXiv:1902.01718 (2019)
Hu, M., et al.: Retrieve, read, rerank: towards end-to-end multi-document reading comprehension. arXiv preprint arXiv:1906.04618 (2019)
Wang, S., Jiang, J.: Machine comprehension using match-LSTM and answer pointer. arXiv preprint arXiv:1608.07905 (2016)
Wang, S., et al.: R 3: reinforced ranker-reader for open-domain question answering. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Wang, Y., et al.: Multi-passage machine reading comprehension with cross-passage answer verification. arXiv preprint arXiv:1805.02220 (2018)
Wang, W., et al.: Gated self-matching networks for reading comprehension and question answering. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2017)
Sun, Y., et al.: ERNIE: enhanced representation through knowledge integration. arXiv preprint arXiv:1904.09223 (2019)
Acknowledgments
This work is supported by National Natural Science Foundation of China No. 61751201, Research Foundation of Beijing Municipal Science and Technology Commission No. Z181100008918002. And we are grateful to Baidu Inc. and China Computer Federation for hosting competition and sharing data resources. We would also like to thank the anonymous reviewers for their insightful suggestions.
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
Ren, M. et al. (2019). Multiple Perspective Answer Reranking for Multi-passage Reading Comprehension. 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_67
Download citation
DOI: https://doi.org/10.1007/978-3-030-32236-6_67
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)
