Abstract
Explainable Multi-Hop Question Answering (MHQA) requires an ability to reason explicitly across facts to arrive at the answer. The majority of multi-hop reasoning methods concentrate on semantic similarity to obtain the next hops or act as entity-centric inference. However, approaches that ignore the rationales required for problems can easily lead to blindness in reasoning. In this paper, we propose a two-Phase text Retrieval method with an entity Mask mechanism (PRM), which focuses on the rationale from global semantics along with entity consideration. Specifically, it consists of two components: 1) The rationale-aware retriever is pre-trained via a dual encoder framework with an entity mask mechanism. The learned representations of hypotheses and facts are utilized to obtain top K candidate core facts by a sentence-level dense retrieval. 2) The entity-aware validator determines the reachability of hypotheses and core facts with an entity granularity sparse matrix. Our experiments on three public datasets in the scientific domain (i.e., OpenbookQA, Worldtree, and ARC-Challenge) demonstrate that the proposed model has achieved remarkable performance over the existing methods.
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
Notes
- 1.
OPT-30B has 30B parameters, and the accuracy on ARC-Challenge is under the zero-shot setting.
- 2.
GPT-3 has 175B parameters, and the accuracy on OpenBookQA is under the zero-shot setting from [25].
References
Asai, A., Hashimoto, K., Hajishirzi, H., Socher, R., Xiong, C.: Learning to retrieve reasoning paths over wikipedia graph for question answering. arXiv preprint arXiv:1911.10470 (2019)
Brown, T.B., et al.: Language models are few-shot learners (2020)
Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051 (2017)
Clark, P., et al.: Think you have solved question answering? Try arc, the AI2 reasoning challenge. arXiv preprint arXiv:1803.05457 (2018)
Demszky, D., Guu, K., Liang, P.: Transforming question answering datasets into natural language inference datasets. arXiv preprint arXiv:1809.02922 (2018)
Dhingra, B., Jin, Q., Yang, Z., Cohen, W.W., Salakhutdinov, R.: Neural models for reasoning over multiple mentions using coreference. arXiv preprint arXiv:1804.05922 (2018)
Feldman, Y., El-Yaniv, R.: Multi-hop paragraph retrieval for open-domain question answering. arXiv preprint arXiv:1906.06606 (2019)
Izacard, G., Grave, E.: Distilling knowledge from reader to retriever for question answering. arXiv preprint arXiv:2012.04584 (2020)
Izacard, G., Grave, E.: Leveraging passage retrieval with generative models for open domain question answering. arXiv preprint arXiv:2007.01282 (2020)
Jansen, P.A., Wainwright, E., Marmorstein, S., Morrison, C.T.: Worldtree: a corpus of explanation graphs for elementary science questions supporting multi-hop inference. arXiv preprint arXiv:1802.03052 (2018)
Wei, J., et al.: Chain of thought prompting elicits reasoning in large language models. arXiv, abs/2201.11903 (2022)
Jiang, Y., Joshi, N., Chen, Y.C., Bansal, M.: Explore, propose, and assemble: an interpretable model for multi-hop reading comprehension. arXiv preprint arXiv:1906.05210 (2019)
Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)
Kundu, S., Khot, T., Sabharwal, A., Clark, P.: Exploiting explicit paths for multi-hop reading comprehension. arXiv preprint arXiv:1811.01127 (2018)
Lan, Y., Jiang, J.: Query graph generation for answering multi-hop complex questions from knowledge bases. Association for Computational Linguistics (2020)
Lin, B.Y., Sun, H., Dhingra, B., Zaheer, M., Ren, X., Cohen, W.W.: Differentiable open-ended commonsense reasoning. arXiv preprint arXiv:2010.14439 (2020)
Mihaylov, T., Clark, P., Khot, T., Sabharwal, A.: Can a suit of armor conduct electricity? A new dataset for open book question answering. arXiv preprint arXiv:1809.02789 (2018)
Pan, X., Yao, W., Zhang, H., Yu, D., Yu, D., Chen, J.: Knowledge-in-context: towards knowledgeable semi-parametric language models. In: The Eleventh International Conference on Learning Representations (2023)
Qi, P., Lin, X., Mehr, L., Wang, Z., Manning, C.D.: Answering complex open-domain questions through iterative query generation. arXiv preprint arXiv:1910.07000 (2019)
Robertson, S., Zaragoza, H., et al.: The probabilistic relevance framework: BM25 and beyond. Found. Trends® Inf. Retrieval 3(4), 333–389 (2009)
Sun, H., Bedrax-Weiss, T., Cohen, W.W.: Pullnet: open domain question answering with iterative retrieval on knowledge bases and text. arXiv preprint arXiv:1904.09537 (2019)
Sun, K., Yu, D., Yu, D., Cardie, C.: Improving machine reading comprehension with general reading strategies. arXiv preprint arXiv:1810.13441 (2018)
Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. arXiv, abs/2205.11916 (2022)
Thayaparan, M., Valentino, M., Freitas, A.: Explanationlp: abductive reasoning for explainable science question answering. arXiv preprint arXiv:2010.13128 (2020)
Touvron, H., et al.: Llama: open and efficient foundation language models (2023)
Valentino, M., Thayaparan, M., Freitas, A.: Case-based abductive natural language inference. arXiv e-prints pp. arXiv-2009 (2020)
Xie, Z., Thiem, S., Martin, J., Wainwright, E., Marmorstein, S., Jansen, P.: Worldtree V2: a corpus of science-domain structured explanations and inference patterns supporting multi-hop inference. In: Proceedings of the 12th Language Resources and Evaluation Conference, pp. 5456–5473 (2020)
Yadav, V., Bethard, S., Surdeanu, M.: Quick and (not so) dirty: unsupervised selection of justification sentences for multi-hop question answering. arXiv preprint arXiv:1911.07176 (2019)
Yang, Z., et al.: Hotpotqa: a dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600 (2018)
Zhang, S., et al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)
Zhou, Z., Valentino, M., Landers, D., Freitas, A.: Encoding explanatory knowledge for zero-shot science question answering. arXiv preprint arXiv:2105.05737 (2021)
Jansen, P., Balasubramanian, N., Surdeanu, M., Clark, P.: What’s in an explanation? characterizing knowledge and inference requirements for elementary science exams. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp. 2956–2965 (2016)
Acknowledgments
This work is supported by the National Natural Science Foundation of China (62172352), the Central leading local science and Technology Development Fund Project (No. 226Z0305G), Project of Hebei Key Laboratory of Software Engineering (22567637H), the Natural Science Foundation of Hebei Province (F20222 03028) and Program for Top 100 Innovative Talents in Colleges and Universities of Hebei Province (CXZZSS2023038).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, Q., Feng, J., Xu, G., Huang, L. (2024). Two-Phase Semantic Retrieval for Explainable Multi-Hop Question Answering. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Lecture Notes in Computer Science, vol 14448. Springer, Singapore. https://doi.org/10.1007/978-981-99-8082-6_35
Download citation
DOI: https://doi.org/10.1007/978-981-99-8082-6_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8081-9
Online ISBN: 978-981-99-8082-6
eBook Packages: Computer ScienceComputer Science (R0)