Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpretable 3-module system called Explore-Propose-Assemble reader (EPAr). First, the Document Explorer iteratively selects relevant documents and represents divergent reasoning chains in a tree structure so as to allow assimilating information from all chains. The Answer Proposer then proposes an answer from every root-to-leaf path in the reasoning tree. Finally, the Evidence Assembler extracts a key sentence containing the proposed answer from every path and combines them to predict the final answer. Intuitively, EPAr approximates the coarse-to-fine-grained comprehension behavior of human readers when facing multiple long documents. We jointly optimize our 3 modules by minimizing the sum of losses from each stage conditioned on the previous stage’s output. On two multi-hop reading comprehension datasets WikiHop and MedHop, our EPAr model achieves significant improvements over the baseline and competitive results compared to the state-of-the-art model. We also present multiple reasoning-chain-recovery tests and ablation studies to demonstrate our system’s ability to perform interpretable and accurate reasoning.
@inproceedings{jiang-etal-2019-explore, title = "Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension", author = "Jiang, Yichen and Joshi, Nitish and Chen, Yen-Chun and Bansal, Mohit", editor = "Korhonen, Anna and Traum, David and M{\`a}rquez, Llu{\'i}s", booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics", month = jul, year = "2019", address = "Florence, Italy", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/P19-1261/", doi = "10.18653/v1/P19-1261", pages = "2714--2725", abstract = "Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpretable 3-module system called Explore-Propose-Assemble reader (EPAr). First, the Document Explorer iteratively selects relevant documents and represents divergent reasoning chains in a tree structure so as to allow assimilating information from all chains. The Answer Proposer then proposes an answer from every root-to-leaf path in the reasoning tree. Finally, the Evidence Assembler extracts a key sentence containing the proposed answer from every path and combines them to predict the final answer. Intuitively, EPAr approximates the coarse-to-fine-grained comprehension behavior of human readers when facing multiple long documents. We jointly optimize our 3 modules by minimizing the sum of losses from each stage conditioned on the previous stage`s output. On two multi-hop reading comprehension datasets WikiHop and MedHop, our EPAr model achieves significant improvements over the baseline and competitive results compared to the state-of-the-art model. We also present multiple reasoning-chain-recovery tests and ablation studies to demonstrate our system`s ability to perform interpretable and accurate reasoning."}
<?xml version="1.0" encoding="UTF-8"?><modsCollection xmlns="http://www.loc.gov/mods/v3"><mods ID="jiang-etal-2019-explore"> <titleInfo> <title>Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension</title> </titleInfo> <name type="personal"> <namePart type="given">Yichen</namePart> <namePart type="family">Jiang</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Nitish</namePart> <namePart type="family">Joshi</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Yen-Chun</namePart> <namePart type="family">Chen</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Mohit</namePart> <namePart type="family">Bansal</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2019-07</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title> </titleInfo> <name type="personal"> <namePart type="given">Anna</namePart> <namePart type="family">Korhonen</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">David</namePart> <namePart type="family">Traum</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Lluís</namePart> <namePart type="family">Màrquez</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>Association for Computational Linguistics</publisher> <place> <placeTerm type="text">Florence, Italy</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpretable 3-module system called Explore-Propose-Assemble reader (EPAr). First, the Document Explorer iteratively selects relevant documents and represents divergent reasoning chains in a tree structure so as to allow assimilating information from all chains. The Answer Proposer then proposes an answer from every root-to-leaf path in the reasoning tree. Finally, the Evidence Assembler extracts a key sentence containing the proposed answer from every path and combines them to predict the final answer. Intuitively, EPAr approximates the coarse-to-fine-grained comprehension behavior of human readers when facing multiple long documents. We jointly optimize our 3 modules by minimizing the sum of losses from each stage conditioned on the previous stage‘s output. On two multi-hop reading comprehension datasets WikiHop and MedHop, our EPAr model achieves significant improvements over the baseline and competitive results compared to the state-of-the-art model. We also present multiple reasoning-chain-recovery tests and ablation studies to demonstrate our system‘s ability to perform interpretable and accurate reasoning.</abstract> <identifier type="citekey">jiang-etal-2019-explore</identifier> <identifier type="doi">10.18653/v1/P19-1261</identifier> <location> <url>https://aclanthology.org/P19-1261/</url> </location> <part> <date>2019-07</date> <extent unit="page"> <start>2714</start> <end>2725</end> </extent> </part></mods></modsCollection>
%0 Conference Proceedings%T Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension%A Jiang, Yichen%A Joshi, Nitish%A Chen, Yen-Chun%A Bansal, Mohit%Y Korhonen, Anna%Y Traum, David%Y Màrquez, Lluís%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics%D 2019%8 July%I Association for Computational Linguistics%C Florence, Italy%F jiang-etal-2019-explore%X Multi-hop reading comprehension requires the model to explore and connect relevant information from multiple sentences/documents in order to answer the question about the context. To achieve this, we propose an interpretable 3-module system called Explore-Propose-Assemble reader (EPAr). First, the Document Explorer iteratively selects relevant documents and represents divergent reasoning chains in a tree structure so as to allow assimilating information from all chains. The Answer Proposer then proposes an answer from every root-to-leaf path in the reasoning tree. Finally, the Evidence Assembler extracts a key sentence containing the proposed answer from every path and combines them to predict the final answer. Intuitively, EPAr approximates the coarse-to-fine-grained comprehension behavior of human readers when facing multiple long documents. We jointly optimize our 3 modules by minimizing the sum of losses from each stage conditioned on the previous stage‘s output. On two multi-hop reading comprehension datasets WikiHop and MedHop, our EPAr model achieves significant improvements over the baseline and competitive results compared to the state-of-the-art model. We also present multiple reasoning-chain-recovery tests and ablation studies to demonstrate our system‘s ability to perform interpretable and accurate reasoning.%R 10.18653/v1/P19-1261%U https://aclanthology.org/P19-1261/%U https://doi.org/10.18653/v1/P19-1261%P 2714-2725
[Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension](https://aclanthology.org/P19-1261/) (Jiang et al., ACL 2019)