<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ji-etal-2023-improving">
    <titleInfo>
        <title>Improving Span Representation by Efficient Span-Level Attention</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pengyu</namePart>
        <namePart type="family">Ji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Songlin</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kewei</namePart>
        <namePart type="family">Tu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>High-quality span representations are crucial to natural language processing tasks involving span prediction and classification. Most existing methods derive a span representation by aggregation of token representations within the span. In contrast, we aim to improve span representations by considering span-span interactions as well as more comprehensive span-token interactions. Specifically, we introduce layers of span-level attention on top of a normal token-level transformer encoder. Given that attention between all span pairs results in O(n⁴) complexity (n being the sentence length) and not all span interactions are intuitively meaningful, we restrict the range of spans that a given span could attend to, thereby reducing overall complexity to O(n³). We conduct experiments on various span-related tasks and show superior performance of our model surpassing baseline models. Our code is publicly available at https://github.com/jipy0222/Span-Level-Attention.</abstract>
    <identifier type="citekey">ji-etal-2023-improving</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.747</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.747</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>11184</start>
            <end>11192</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Span Representation by Efficient Span-Level Attention
%A Ji, Pengyu
%A Yang, Songlin
%A Tu, Kewei
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F ji-etal-2023-improving
%X High-quality span representations are crucial to natural language processing tasks involving span prediction and classification. Most existing methods derive a span representation by aggregation of token representations within the span. In contrast, we aim to improve span representations by considering span-span interactions as well as more comprehensive span-token interactions. Specifically, we introduce layers of span-level attention on top of a normal token-level transformer encoder. Given that attention between all span pairs results in O(n⁴) complexity (n being the sentence length) and not all span interactions are intuitively meaningful, we restrict the range of spans that a given span could attend to, thereby reducing overall complexity to O(n³). We conduct experiments on various span-related tasks and show superior performance of our model surpassing baseline models. Our code is publicly available at https://github.com/jipy0222/Span-Level-Attention.
%R 10.18653/v1/2023.findings-emnlp.747
%U https://aclanthology.org/2023.findings-emnlp.747
%U https://doi.org/10.18653/v1/2023.findings-emnlp.747
%P 11184-11192

Markdown (Informal)

[Improving Span Representation by Efficient Span-Level Attention](https://aclanthology.org/2023.findings-emnlp.747) (Ji et al., Findings 2023)

• Improving Span Representation by Efficient Span-Level Attention (Ji et al., Findings 2023)

ACL

• Pengyu Ji, Songlin Yang, and Kewei Tu. 2023. Improving Span Representation by Efficient Span-Level Attention. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 11184–11192, Singapore. Association for Computational Linguistics.