Abstract
Question answering (QA) systems can be classified as either text-based QA systems or knowledge base QA (KBQA) systems, depending on the used knowledge source. KBQA systems are generally domain-specific and can’t deal with a variety of questions in the open-domain QA setting, while text-based systems can. However, text-based systems’ performance is far from satisfactory. This paper focuses on the text-based open-domain QA setting. We argue that text-based approaches’ poor performance is largely caused by the lack of knowledge, which is often essential for answering the question and can be easily found in knowledge base (KB), in plain text. So in this paper, we propose a new text-based open-domain QA system called KF (Knowledge Fusion)-QA, which uses KB as a second knowledge source to incorporate essential knowledge into text to help answer the question. Our system has a Knowledge-Aware Encoder which extracts essential knowledge from KB and performs knowledge fusion to output knowledge-aware (KA) text representations. With this KA representations, the system first re-rank the retrieved documents, then read the re-ranked top-N documents to give the answer. Our system significantly outperforms existing text-based QA systems on multiple open-domain QA datasets, demonstrating the effectiveness of fusing essential knowledge.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Berant, J., Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer pairs. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1533–1544 (2013)
Bollacker, K., Evans, C., Paritosh, P., Sturge, T., Taylor, J.: Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, pp. 1247–1250 (2008)
Cer, D., et al.: Universal sentence encoder. arXiv preprint arXiv:1803.11175 (2018)
Chen, D., Bolton, J., Manning, C.D.: A thorough examination of the CNN/daily mail reading comprehension task. arXiv preprint arXiv:1606.02858 (2016)
Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading Wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051 (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)
Dhingra, B., Mazaitis, K., Cohen, W.W.: Quasar: datasets for question answering by search and reading. arXiv preprint arXiv:1707.03904 (2017)
Ferragina, P., Scaiella, U.: TAGME: on-the-fly annotation of short text fragments (by Wikipedia entities). In: Proceedings of the 19th ACM International Conference on Information and Knowledge Management, pp. 1625–1628 (2010)
Haveliwala, T.H.: Topic-sensitive PageRank: a context-sensitive ranking algorithm for web search. IEEE Trans. Knowl. Data Eng. 15(4), 784–796 (2003)
Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)
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 (Long Papers), vol. 1, pp. 1736–1745 (2018)
Miller, A., Fisch, A., Dodge, J., Karimi, A.H., Bordes, A., Weston, J.: Key-value memory networks for directly reading documents. arXiv preprint arXiv:1606.03126 (2016)
Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)
Sun, H., Dhingra, B., Zaheer, M., Mazaitis, K., Salakhutdinov, R., Cohen, W.W.: Open domain question answering using early fusion of knowledge bases and text. arXiv preprint arXiv:1809.00782 (2018)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
Wang, S., et al.: R 3: Reinforced ranker-reader for open-domain question answering. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Xiong, W., Yu, M., Chang, S., Guo, X., Wang, W.Y.: Improving question answering over incomplete KBs with knowledge-aware reader. arXiv preprint arXiv:1905.07098 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Su, X., Li, Y., Wu, Z. (2021). Fusing Essential Knowledge for Text-Based Open-Domain Question Answering. In: Karlapalem, K., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2021. Lecture Notes in Computer Science(), vol 12713. Springer, Cham. https://doi.org/10.1007/978-3-030-75765-6_50
Download citation
DOI: https://doi.org/10.1007/978-3-030-75765-6_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75764-9
Online ISBN: 978-3-030-75765-6
eBook Packages: Computer ScienceComputer Science (R0)