<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhuang-wang-2019-token">
    <titleInfo>
        <title>Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yimeng</namePart>
        <namePart type="family">Zhuang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huadong</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multi-passage reading comprehension requires the ability to combine cross-passage information and reason over multiple passages to infer the answer. In this paper, we introduce the Dynamic Self-attention Network (DynSAN) for multi-passage reading comprehension task, which processes cross-passage information at token-level and meanwhile avoids substantial computational costs. The core module of the dynamic self-attention is a proposed gated token selection mechanism, which dynamically selects important tokens from a sequence. These chosen tokens will attend to each other via a self-attention mechanism to model long-range dependencies. Besides, convolutional layers are combined with the dynamic self-attention to enhance the model’s capacity of extracting local semantic. The experimental results show that the proposed DynSAN achieves new state-of-the-art performance on the SearchQA, Quasar-T and WikiHop datasets. Further ablation study also validates the effectiveness of our model components.</abstract>
    <identifier type="citekey">zhuang-wang-2019-token</identifier>
    <identifier type="doi">10.18653/v1/P19-1218</identifier>
    <location>
        <url>https://aclanthology.org/P19-1218</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>2252</start>
            <end>2262</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension
%A Zhuang, Yimeng
%A Wang, Huadong
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F zhuang-wang-2019-token
%X Multi-passage reading comprehension requires the ability to combine cross-passage information and reason over multiple passages to infer the answer. In this paper, we introduce the Dynamic Self-attention Network (DynSAN) for multi-passage reading comprehension task, which processes cross-passage information at token-level and meanwhile avoids substantial computational costs. The core module of the dynamic self-attention is a proposed gated token selection mechanism, which dynamically selects important tokens from a sequence. These chosen tokens will attend to each other via a self-attention mechanism to model long-range dependencies. Besides, convolutional layers are combined with the dynamic self-attention to enhance the model’s capacity of extracting local semantic. The experimental results show that the proposed DynSAN achieves new state-of-the-art performance on the SearchQA, Quasar-T and WikiHop datasets. Further ablation study also validates the effectiveness of our model components.
%R 10.18653/v1/P19-1218
%U https://aclanthology.org/P19-1218
%U https://doi.org/10.18653/v1/P19-1218
%P 2252-2262

Markdown (Informal)

[Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension](https://aclanthology.org/P19-1218) (Zhuang & Wang, ACL 2019)

• Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension (Zhuang & Wang, ACL 2019)

ACL

• Yimeng Zhuang and Huadong Wang. 2019. Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2252–2262, Florence, Italy. Association for Computational Linguistics.