<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-unsupervised">
    <titleInfo>
        <title>Unsupervised Conversation Disentanglement through Co-Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hui</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhan</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaodan</namePart>
        <namePart type="family">Zhu</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 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Conversation disentanglement aims to separate intermingled messages into detached sessions, which is a fundamental task in understanding multi-party conversations. Existing work on conversation disentanglement relies heavily upon human-annotated datasets, which is expensive to obtain in practice. In this work, we explore training a conversation disentanglement model without referencing any human annotations. Our method is built upon the deep co-training algorithm, which consists of two neural networks: a message-pair classifier and a session classifier. The former is responsible of retrieving local relations between two messages while the latter categorizes a message to a session by capturing context-aware information. Both the two networks are initialized respectively with pseudo data built from the unannotated corpus. During the deep co-training process, we use the session classifier as a reinforcement learning component to learn a session assigning policy by maximizing the local rewards given by the message-pair classifier. For the message-pair classifier, we enrich its training data by retrieving message pairs with high confidence from the disentangled sessions predicted by the session classifier. Experimental results on the large Movie Dialogue Dataset demonstrate that our proposed approach achieves competitive performance compared to previous supervised methods. Further experiments show that the predicted disentangled conversations can promote the performance on the downstream task of multi-party response selection.</abstract>
    <identifier type="citekey">liu-etal-2021-unsupervised</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.181</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.181</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>2345</start>
            <end>2356</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Unsupervised Conversation Disentanglement through Co-Training
%A Liu, Hui
%A Shi, Zhan
%A Zhu, Xiaodan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F liu-etal-2021-unsupervised
%X Conversation disentanglement aims to separate intermingled messages into detached sessions, which is a fundamental task in understanding multi-party conversations. Existing work on conversation disentanglement relies heavily upon human-annotated datasets, which is expensive to obtain in practice. In this work, we explore training a conversation disentanglement model without referencing any human annotations. Our method is built upon the deep co-training algorithm, which consists of two neural networks: a message-pair classifier and a session classifier. The former is responsible of retrieving local relations between two messages while the latter categorizes a message to a session by capturing context-aware information. Both the two networks are initialized respectively with pseudo data built from the unannotated corpus. During the deep co-training process, we use the session classifier as a reinforcement learning component to learn a session assigning policy by maximizing the local rewards given by the message-pair classifier. For the message-pair classifier, we enrich its training data by retrieving message pairs with high confidence from the disentangled sessions predicted by the session classifier. Experimental results on the large Movie Dialogue Dataset demonstrate that our proposed approach achieves competitive performance compared to previous supervised methods. Further experiments show that the predicted disentangled conversations can promote the performance on the downstream task of multi-party response selection.
%R 10.18653/v1/2021.emnlp-main.181
%U https://aclanthology.org/2021.emnlp-main.181
%U https://doi.org/10.18653/v1/2021.emnlp-main.181
%P 2345-2356

Markdown (Informal)

[Unsupervised Conversation Disentanglement through Co-Training](https://aclanthology.org/2021.emnlp-main.181) (Liu et al., EMNLP 2021)

• Unsupervised Conversation Disentanglement through Co-Training (Liu et al., EMNLP 2021)

ACL

• Hui Liu, Zhan Shi, and Xiaodan Zhu. 2021. Unsupervised Conversation Disentanglement through Co-Training. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2345–2356, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.