@inproceedings{cheng-etal-2020-probabilistic,
title = "Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering",
author = "Cheng, Hao and
Chang, Ming-Wei and
Lee, Kenton and
Toutanova, Kristina",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.501",
doi = "10.18653/v1/2020.acl-main.501",
pages = "5657--5667",
abstract = "We address the problem of extractive question answering using document-level distant super-vision, pairing questions and relevant documents with answer strings. We compare previously used probability space and distant supervision assumptions (assumptions on the correspondence between the weak answer string labels and possible answer mention spans). We show that these assumptions interact, and that different configurations provide complementary benefits. We demonstrate that a multi-objective model can efficiently combine the advantages of multiple assumptions and outperform the best individual formulation. Our approach outperforms previous state-of-the-art models by 4.3 points in F1 on TriviaQA-Wiki and 1.7 points in Rouge-L on NarrativeQA summaries.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2020-probabilistic">
<titleInfo>
<title>Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenton</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We address the problem of extractive question answering using document-level distant super-vision, pairing questions and relevant documents with answer strings. We compare previously used probability space and distant supervision assumptions (assumptions on the correspondence between the weak answer string labels and possible answer mention spans). We show that these assumptions interact, and that different configurations provide complementary benefits. We demonstrate that a multi-objective model can efficiently combine the advantages of multiple assumptions and outperform the best individual formulation. Our approach outperforms previous state-of-the-art models by 4.3 points in F1 on TriviaQA-Wiki and 1.7 points in Rouge-L on NarrativeQA summaries.</abstract>
<identifier type="citekey">cheng-etal-2020-probabilistic</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.501</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.501</url>
</location>
<part>
<date>2020-jul</date>
<extent unit="page">
<start>5657</start>
<end>5667</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering
%A Cheng, Hao
%A Chang, Ming-Wei
%A Lee, Kenton
%A Toutanova, Kristina
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 jul
%I Association for Computational Linguistics
%C Online
%F cheng-etal-2020-probabilistic
%X We address the problem of extractive question answering using document-level distant super-vision, pairing questions and relevant documents with answer strings. We compare previously used probability space and distant supervision assumptions (assumptions on the correspondence between the weak answer string labels and possible answer mention spans). We show that these assumptions interact, and that different configurations provide complementary benefits. We demonstrate that a multi-objective model can efficiently combine the advantages of multiple assumptions and outperform the best individual formulation. Our approach outperforms previous state-of-the-art models by 4.3 points in F1 on TriviaQA-Wiki and 1.7 points in Rouge-L on NarrativeQA summaries.
%R 10.18653/v1/2020.acl-main.501
%U https://aclanthology.org/2020.acl-main.501
%U https://doi.org/10.18653/v1/2020.acl-main.501
%P 5657-5667
Markdown (Informal)
[Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering](https://aclanthology.org/2020.acl-main.501) (Cheng et al., ACL 2020)
ACL