<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kulkarni-etal-2023-empirical">
    <titleInfo>
        <title>An Empirical Analysis of Leveraging Knowledge for Low-Resource Task-Oriented Semantic Parsing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mayank</namePart>
        <namePart type="family">Kulkarni</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aoxiao</namePart>
        <namePart type="family">Zhong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicolas</namePart>
        <namePart type="family">Guenon des mesnards</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sahar</namePart>
        <namePart type="family">Movaghati</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mukund</namePart>
        <namePart type="family">Sridhar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">He</namePart>
        <namePart type="family">Xie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianhua</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Task-oriented semantic parsing has drawn a lot of interest from the NLP community, and especially the voice assistant industry as it enables representing the meaning of user requests with arbitrarily nested semantics, including multiple intents and compound entities. SOTA models are large seq2seq transformers and require hundreds of thousands of annotated examples to be trained. However annotating such data to bootstrap new domains or languages is expensive and error-prone, especially for requests made of nested semantics. In addition large models easily break the tight latency constraints imposed in a user-facing production environment. As part of this work we explore leveraging external knowledge to improve model accuracy in low-resource and low-compute settings. We demonstrate that using knowledge-enhanced encoders inside seq2seq models does not result in performance gains by itself, but jointly learning to uncover entities in addition to the parse generation is a simple yet effective way of improving performance across the board. We show this is especially true in the low-compute scarce-data setting and for entity-rich domains, with relative gains up to 74.48% on the TOPv2 dataset.</abstract>
    <identifier type="citekey">kulkarni-etal-2023-empirical</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.123</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.123</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>1955</start>
            <end>1969</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T An Empirical Analysis of Leveraging Knowledge for Low-Resource Task-Oriented Semantic Parsing
%A Kulkarni, Mayank
%A Zhong, Aoxiao
%A Guenon des mesnards, Nicolas
%A Movaghati, Sahar
%A Sridhar, Mukund
%A Xie, He
%A Lu, Jianhua
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kulkarni-etal-2023-empirical
%X Task-oriented semantic parsing has drawn a lot of interest from the NLP community, and especially the voice assistant industry as it enables representing the meaning of user requests with arbitrarily nested semantics, including multiple intents and compound entities. SOTA models are large seq2seq transformers and require hundreds of thousands of annotated examples to be trained. However annotating such data to bootstrap new domains or languages is expensive and error-prone, especially for requests made of nested semantics. In addition large models easily break the tight latency constraints imposed in a user-facing production environment. As part of this work we explore leveraging external knowledge to improve model accuracy in low-resource and low-compute settings. We demonstrate that using knowledge-enhanced encoders inside seq2seq models does not result in performance gains by itself, but jointly learning to uncover entities in addition to the parse generation is a simple yet effective way of improving performance across the board. We show this is especially true in the low-compute scarce-data setting and for entity-rich domains, with relative gains up to 74.48% on the TOPv2 dataset.
%R 10.18653/v1/2023.findings-acl.123
%U https://aclanthology.org/2023.findings-acl.123
%U https://doi.org/10.18653/v1/2023.findings-acl.123
%P 1955-1969

Markdown (Informal)

[An Empirical Analysis of Leveraging Knowledge for Low-Resource Task-Oriented Semantic Parsing](https://aclanthology.org/2023.findings-acl.123) (Kulkarni et al., Findings 2023)

• An Empirical Analysis of Leveraging Knowledge for Low-Resource Task-Oriented Semantic Parsing (Kulkarni et al., Findings 2023)

ACL

• Mayank Kulkarni, Aoxiao Zhong, Nicolas Guenon des mesnards, Sahar Movaghati, Mukund Sridhar, He Xie, and Jianhua Lu. 2023. An Empirical Analysis of Leveraging Knowledge for Low-Resource Task-Oriented Semantic Parsing. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1955–1969, Toronto, Canada. Association for Computational Linguistics.