<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaddy-etal-2021-overcoming">
    <titleInfo>
        <title>Overcoming Conflicting Data when Updating a Neural Semantic Parser</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Gaddy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alex</namePart>
        <namePart type="family">Kouzemtchenko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pavankumar</namePart>
        <namePart type="given">Reddy</namePart>
        <namePart type="family">Muddireddy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Prateek</namePart>
        <namePart type="family">Kolhar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rushin</namePart>
        <namePart type="family">Shah</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Alexandros</namePart>
            <namePart type="family">Papangelis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Paweł</namePart>
            <namePart type="family">Budzianowski</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bing</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Elnaz</namePart>
            <namePart type="family">Nouri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abhinav</namePart>
            <namePart type="family">Rastogi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</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>In this paper, we explore how to use a small amount of new data to update a task-oriented semantic parsing model when the desired output for some examples has changed. When making updates in this way, one potential problem that arises is the presence of conflicting data, or out-of-date labels in the original training set. To evaluate the impact of this understudied problem, we propose an experimental setup for simulating changes to a neural semantic parser. We show that the presence of conflicting data greatly hinders learning of an update, then explore several methods to mitigate its effect. Our multi-task and data selection methods lead to large improvements in model accuracy compared to a naive data-mixing strategy, and our best method closes 86% of the accuracy gap between this baseline and an oracle upper bound.</abstract>
    <identifier type="citekey">gaddy-etal-2021-overcoming</identifier>
    <identifier type="doi">10.18653/v1/2021.nlp4convai-1.5</identifier>
    <location>
        <url>https://aclanthology.org/2021.nlp4convai-1.5</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>40</start>
            <end>51</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Overcoming Conflicting Data when Updating a Neural Semantic Parser
%A Gaddy, David
%A Kouzemtchenko, Alex
%A Muddireddy, Pavankumar Reddy
%A Kolhar, Prateek
%A Shah, Rushin
%Y Papangelis, Alexandros
%Y Budzianowski, Paweł
%Y Liu, Bing
%Y Nouri, Elnaz
%Y Rastogi, Abhinav
%Y Chen, Yun-Nung
%S Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F gaddy-etal-2021-overcoming
%X In this paper, we explore how to use a small amount of new data to update a task-oriented semantic parsing model when the desired output for some examples has changed. When making updates in this way, one potential problem that arises is the presence of conflicting data, or out-of-date labels in the original training set. To evaluate the impact of this understudied problem, we propose an experimental setup for simulating changes to a neural semantic parser. We show that the presence of conflicting data greatly hinders learning of an update, then explore several methods to mitigate its effect. Our multi-task and data selection methods lead to large improvements in model accuracy compared to a naive data-mixing strategy, and our best method closes 86% of the accuracy gap between this baseline and an oracle upper bound.
%R 10.18653/v1/2021.nlp4convai-1.5
%U https://aclanthology.org/2021.nlp4convai-1.5
%U https://doi.org/10.18653/v1/2021.nlp4convai-1.5
%P 40-51

Markdown (Informal)

[Overcoming Conflicting Data when Updating a Neural Semantic Parser](https://aclanthology.org/2021.nlp4convai-1.5) (Gaddy et al., NLP4ConvAI 2021)

• Overcoming Conflicting Data when Updating a Neural Semantic Parser (Gaddy et al., NLP4ConvAI 2021)

ACL

• David Gaddy, Alex Kouzemtchenko, Pavankumar Reddy Muddireddy, Prateek Kolhar, and Rushin Shah. 2021. Overcoming Conflicting Data when Updating a Neural Semantic Parser. In Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI, pages 40–51, Online. Association for Computational Linguistics.