<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shao-etal-2020-graph">
    <titleInfo>
        <title>Is Graph Structure Necessary for Multi-hop Question Answering?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Nan</namePart>
        <namePart type="family">Shao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yiming</namePart>
        <namePart type="family">Cui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ting</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shijin</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guoping</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bonnie</namePart>
            <namePart type="family">Webber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recently, attempting to model texts as graph structure and introducing graph neural networks to deal with it has become a trend in many NLP research areas. In this paper, we investigate whether the graph structure is necessary for textual multi-hop reasoning. Our analysis is centered on HotpotQA. We construct a strong baseline model to establish that, with the proper use of pre-trained models, graph structure may not be necessary for textual multi-hop reasoning. We point out that both graph structure and adjacency matrix are task-related prior knowledge, and graph-attention can be considered as a special case of self-attention. Experiments demonstrate that graph-attention or the entire graph structure can be replaced by self-attention or Transformers.</abstract>
    <identifier type="citekey">shao-etal-2020-graph</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.583</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.583</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>7187</start>
            <end>7192</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Is Graph Structure Necessary for Multi-hop Question Answering?
%A Shao, Nan
%A Cui, Yiming
%A Liu, Ting
%A Wang, Shijin
%A Hu, Guoping
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F shao-etal-2020-graph
%X Recently, attempting to model texts as graph structure and introducing graph neural networks to deal with it has become a trend in many NLP research areas. In this paper, we investigate whether the graph structure is necessary for textual multi-hop reasoning. Our analysis is centered on HotpotQA. We construct a strong baseline model to establish that, with the proper use of pre-trained models, graph structure may not be necessary for textual multi-hop reasoning. We point out that both graph structure and adjacency matrix are task-related prior knowledge, and graph-attention can be considered as a special case of self-attention. Experiments demonstrate that graph-attention or the entire graph structure can be replaced by self-attention or Transformers.
%R 10.18653/v1/2020.emnlp-main.583
%U https://aclanthology.org/2020.emnlp-main.583
%U https://doi.org/10.18653/v1/2020.emnlp-main.583
%P 7187-7192

Markdown (Informal)

[Is Graph Structure Necessary for Multi-hop Question Answering?](https://aclanthology.org/2020.emnlp-main.583) (Shao et al., EMNLP 2020)

• Is Graph Structure Necessary for Multi-hop Question Answering? (Shao et al., EMNLP 2020)

ACL

• Nan Shao, Yiming Cui, Ting Liu, Shijin Wang, and Guoping Hu. 2020. Is Graph Structure Necessary for Multi-hop Question Answering?. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7187–7192, Online. Association for Computational Linguistics.