<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nie-etal-2019-learning">
    <titleInfo>
        <title>Learning to Explain: Answering Why-Questions via Rephrasing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Allen</namePart>
        <namePart type="family">Nie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Erin</namePart>
        <namePart type="family">Bennett</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Noah</namePart>
        <namePart type="family">Goodman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-aug</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on NLP for Conversational AI</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning. Previous work has either relied on human-curated structured knowledge bases or detailed domain representation to generate satisfactory explanations. They are also often limited to ranking pre-existing explanation choices. In our work, we contribute to the under-explored area of generating natural language explanations for general phenomena. We automatically collect large datasets of explanation-phenomenon pairs which allow us to train sequence-to-sequence models to generate natural language explanations. We compare different training strategies and evaluate their performance using both automatic scores and human ratings. We demonstrate that our strategy is sufficient to generate highly plausible explanations for general open-domain phenomena compared to other models trained on different datasets.</abstract>
    <identifier type="citekey">nie-etal-2019-learning</identifier>
    <identifier type="doi">10.18653/v1/W19-4113</identifier>
    <location>
        <url>https://aclanthology.org/W19-4113</url>
    </location>
    <part>
        <date>2019-aug</date>
        <extent unit="page">
            <start>113</start>
            <end>120</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning to Explain: Answering Why-Questions via Rephrasing
%A Nie, Allen
%A Bennett, Erin
%A Goodman, Noah
%S Proceedings of the First Workshop on NLP for Conversational AI
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F nie-etal-2019-learning
%X Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning. Previous work has either relied on human-curated structured knowledge bases or detailed domain representation to generate satisfactory explanations. They are also often limited to ranking pre-existing explanation choices. In our work, we contribute to the under-explored area of generating natural language explanations for general phenomena. We automatically collect large datasets of explanation-phenomenon pairs which allow us to train sequence-to-sequence models to generate natural language explanations. We compare different training strategies and evaluate their performance using both automatic scores and human ratings. We demonstrate that our strategy is sufficient to generate highly plausible explanations for general open-domain phenomena compared to other models trained on different datasets.
%R 10.18653/v1/W19-4113
%U https://aclanthology.org/W19-4113
%U https://doi.org/10.18653/v1/W19-4113
%P 113-120

Markdown (Informal)

[Learning to Explain: Answering Why-Questions via Rephrasing](https://aclanthology.org/W19-4113) (Nie et al., 2019)

• Learning to Explain: Answering Why-Questions via Rephrasing (Nie et al., 2019)

ACL

• Allen Nie, Erin Bennett, and Noah Goodman. 2019. Learning to Explain: Answering Why-Questions via Rephrasing. In Proceedings of the First Workshop on NLP for Conversational AI, pages 113–120, Florence, Italy. Association for Computational Linguistics.