TY - GEN
T1 - Unsupervised alignment-based iterative evidence retrieval for multi-hop question answering
AU - Yadav, Vikas
AU - Bethard, Steven
AU - Surdeanu, Mihai
N1 - Funding Information:
We thank Tushar Khot (AI2) and Daniel Khashabhi (AI2) for helping us with the dataset and evaluation resources. This work was supported by the Defense Advanced Research Projects Agency (DARPA) under the World Modelers program, grant number W911NF1810014. Mihai Surdeanu declares a financial interest in lum.ai. This interest has been properly disclosed to the University of Arizona Institutional Review Committee and is managed in accordance with its conflict of interest policies.
Publisher Copyright:
© 2020 Association for Computational Linguistics
PY - 2020
Y1 - 2020
N2 - Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method. We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) a stopping criterion that terminates retrieval when the terms in the given question and candidate answers are covered by the retrieved justifications. Despite its simplicity, our approach outperforms all the previous methods (including supervised methods) on the evidence selection task on two datasets: MultiRC and QASC. When these evidence sentences are fed into a RoBERTa answer classification component, we achieve state-of-the-art QA performance on these two datasets.
AB - Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method. We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) a stopping criterion that terminates retrieval when the terms in the given question and candidate answers are covered by the retrieved justifications. Despite its simplicity, our approach outperforms all the previous methods (including supervised methods) on the evidence selection task on two datasets: MultiRC and QASC. When these evidence sentences are fed into a RoBERTa answer classification component, we achieve state-of-the-art QA performance on these two datasets.
UR - http://www.scopus.com/inward/record.url?scp=85106190153&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85106190153&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85106190153
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 4514
EP - 4525
BT - ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Y2 - 5 July 2020 through 10 July 2020
ER -