<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deng-etal-2023-intent">
    <titleInfo>
        <title>Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wentao</namePart>
        <namePart type="family">Deng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiahuan</namePart>
        <namePart type="family">Pei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhaochun</namePart>
        <namePart type="family">Ren</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhumin</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pengjie</namePart>
        <namePart type="family">Ren</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Answer selection in open-domain dialogues aims to select an accurate answer from candidates. The recent success of answer selection models hinges on training with large amounts of labeled data. However, collecting large-scale labeled data is labor-intensive and time-consuming. In this paper, we introduce the predicted intent labels to calibrate answer labels in a self-training paradigm. Specifically, we propose intent-calibrated self-training (ICAST) to improve the quality of pseudo answer labels through the intent-calibrated answer selection paradigm, in which we employ pseudo intent labels to help improve pseudo answer labels. We carry out extensive experiments on two benchmark datasets with open-domain dialogues. The experimental results show that ICAST outperforms baselines consistently with 1%, 5%, and 10% labeled data. Specifically, it improves 2.06% and 1.00% of F1 score on the two datasets, compared with the strongest baseline with only 5% labeled data.</abstract>
    <identifier type="citekey">deng-etal-2023-intent</identifier>
    <identifier type="doi">10.1162/tacl_a_00599</identifier>
    <location>
        <url>https://aclanthology.org/2023.tacl-1.70/</url>
    </location>
    <part>
        <date>2023</date>
        <detail type="volume"><number>11</number></detail>
        <extent unit="page">
            <start>1232</start>
            <end>1249</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues
%A Deng, Wentao
%A Pei, Jiahuan
%A Ren, Zhaochun
%A Chen, Zhumin
%A Ren, Pengjie
%J Transactions of the Association for Computational Linguistics
%D 2023
%V 11
%I MIT Press
%C Cambridge, MA
%F deng-etal-2023-intent
%X Answer selection in open-domain dialogues aims to select an accurate answer from candidates. The recent success of answer selection models hinges on training with large amounts of labeled data. However, collecting large-scale labeled data is labor-intensive and time-consuming. In this paper, we introduce the predicted intent labels to calibrate answer labels in a self-training paradigm. Specifically, we propose intent-calibrated self-training (ICAST) to improve the quality of pseudo answer labels through the intent-calibrated answer selection paradigm, in which we employ pseudo intent labels to help improve pseudo answer labels. We carry out extensive experiments on two benchmark datasets with open-domain dialogues. The experimental results show that ICAST outperforms baselines consistently with 1%, 5%, and 10% labeled data. Specifically, it improves 2.06% and 1.00% of F1 score on the two datasets, compared with the strongest baseline with only 5% labeled data.
%R 10.1162/tacl_a_00599
%U https://aclanthology.org/2023.tacl-1.70/
%U https://doi.org/10.1162/tacl_a_00599
%P 1232-1249

Markdown (Informal)

[Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues](https://aclanthology.org/2023.tacl-1.70/) (Deng et al., TACL 2023)

• Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues (Deng et al., TACL 2023)

ACL

• Wentao Deng, Jiahuan Pei, Zhaochun Ren, Zhumin Chen, and Pengjie Ren. 2023. Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues. Transactions of the Association for Computational Linguistics, 11:1232–1249.