<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yasunaga-etal-2021-qa">
    <titleInfo>
        <title>QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Michihiro</namePart>
        <namePart type="family">Yasunaga</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongyu</namePart>
        <namePart type="family">Ren</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Antoine</namePart>
        <namePart type="family">Bosselut</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Percy</namePart>
        <namePart type="family">Liang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jure</namePart>
        <namePart type="family">Leskovec</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-jun</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</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>The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG. Here we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: (i) relevance scoring, where we use LMs to estimate the importance of KG nodes relative to the given QA context, and (ii) joint reasoning, where we connect the QA context and KG to form a joint graph, and mutually update their representations through graph-based message passing. We evaluate QA-GNN on the CommonsenseQA and OpenBookQA datasets, and show its improvement over existing LM and LM+KG models, as well as its capability to perform interpretable and structured reasoning, e.g., correctly handling negation in questions.</abstract>
    <identifier type="citekey">yasunaga-etal-2021-qa</identifier>
    <identifier type="doi">10.18653/v1/2021.naacl-main.45</identifier>
    <location>
        <url>https://aclanthology.org/2021.naacl-main.45</url>
    </location>
    <part>
        <date>2021-jun</date>
        <extent unit="page">
            <start>535</start>
            <end>546</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
%A Yasunaga, Michihiro
%A Ren, Hongyu
%A Bosselut, Antoine
%A Liang, Percy
%A Leskovec, Jure
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F yasunaga-etal-2021-qa
%X The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG. Here we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: (i) relevance scoring, where we use LMs to estimate the importance of KG nodes relative to the given QA context, and (ii) joint reasoning, where we connect the QA context and KG to form a joint graph, and mutually update their representations through graph-based message passing. We evaluate QA-GNN on the CommonsenseQA and OpenBookQA datasets, and show its improvement over existing LM and LM+KG models, as well as its capability to perform interpretable and structured reasoning, e.g., correctly handling negation in questions.
%R 10.18653/v1/2021.naacl-main.45
%U https://aclanthology.org/2021.naacl-main.45
%U https://doi.org/10.18653/v1/2021.naacl-main.45
%P 535-546

Markdown (Informal)

[QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://aclanthology.org/2021.naacl-main.45) (Yasunaga et al., NAACL 2021)

• QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering (Yasunaga et al., NAACL 2021)

ACL

• Michihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, and Jure Leskovec. 2021. QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 535–546, Online. Association for Computational Linguistics.