@inproceedings{yadav-etal-2019-quick,
title = "Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering",
author = "Yadav, Vikas and
Bethard, Steven and
Surdeanu, Mihai",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1260",
doi = "10.18653/v1/D19-1260",
pages = "2578--2589",
abstract = "We propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that (a) maximizes the relevance of the selected sentences, (b) minimizes the overlap between the selected facts, and (c) maximizes the coverage of both question and answer. This unsupervised sentence selection can be coupled with any supervised QA model. We show that the sentences selected by our method improve the performance of a state-of-the-art supervised QA model on two multi-hop QA datasets: AI2{'}s Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC). We obtain new state-of-the-art performance on both datasets among systems that do not use external resources for training the QA system: 56.82{\%} F1 on ARC (41.24{\%} on Challenge and 64.49{\%} on Easy) and 26.1{\%} EM0 on MultiRC. Our justification sentences have higher quality than the justifications selected by a strong information retrieval baseline, e.g., by 5.4{\%} F1 in MultiRC. We also show that our unsupervised selection of justification sentences is more stable across domains than a state-of-the-art supervised sentence selection method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-etal-2019-quick">
<titleInfo>
<title>Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vikas</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that (a) maximizes the relevance of the selected sentences, (b) minimizes the overlap between the selected facts, and (c) maximizes the coverage of both question and answer. This unsupervised sentence selection can be coupled with any supervised QA model. We show that the sentences selected by our method improve the performance of a state-of-the-art supervised QA model on two multi-hop QA datasets: AI2’s Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC). We obtain new state-of-the-art performance on both datasets among systems that do not use external resources for training the QA system: 56.82% F1 on ARC (41.24% on Challenge and 64.49% on Easy) and 26.1% EM0 on MultiRC. Our justification sentences have higher quality than the justifications selected by a strong information retrieval baseline, e.g., by 5.4% F1 in MultiRC. We also show that our unsupervised selection of justification sentences is more stable across domains than a state-of-the-art supervised sentence selection method.</abstract>
<identifier type="citekey">yadav-etal-2019-quick</identifier>
<identifier type="doi">10.18653/v1/D19-1260</identifier>
<location>
<url>https://aclanthology.org/D19-1260</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>2578</start>
<end>2589</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering
%A Yadav, Vikas
%A Bethard, Steven
%A Surdeanu, Mihai
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F yadav-etal-2019-quick
%X We propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that (a) maximizes the relevance of the selected sentences, (b) minimizes the overlap between the selected facts, and (c) maximizes the coverage of both question and answer. This unsupervised sentence selection can be coupled with any supervised QA model. We show that the sentences selected by our method improve the performance of a state-of-the-art supervised QA model on two multi-hop QA datasets: AI2’s Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC). We obtain new state-of-the-art performance on both datasets among systems that do not use external resources for training the QA system: 56.82% F1 on ARC (41.24% on Challenge and 64.49% on Easy) and 26.1% EM0 on MultiRC. Our justification sentences have higher quality than the justifications selected by a strong information retrieval baseline, e.g., by 5.4% F1 in MultiRC. We also show that our unsupervised selection of justification sentences is more stable across domains than a state-of-the-art supervised sentence selection method.
%R 10.18653/v1/D19-1260
%U https://aclanthology.org/D19-1260
%U https://doi.org/10.18653/v1/D19-1260
%P 2578-2589
Markdown (Informal)
[Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering](https://aclanthology.org/D19-1260) (Yadav et al., EMNLP-IJCNLP 2019)
ACL