<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2021-findings">
    <titleInfo>
        <title>Findings on Conversation Disentanglement</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rongxin</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jey</namePart>
        <namePart type="given">Han</namePart>
        <namePart type="family">Lau</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianzhong</namePart>
        <namePart type="family">Qi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Afshin</namePart>
            <namePart type="family">Rahimi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">William</namePart>
            <namePart type="family">Lane</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Guido</namePart>
            <namePart type="family">Zuccon</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Australasian Language Technology Association</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Conversation disentanglement, the task to identify separate threads in conversations, is an important pre-processing step in multi-party conversational NLP applications such as conversational question answering and con-versation summarization. Framing it as a utterance-to-utterance classification problem — i.e. given an utterance of interest (UOI), find which past utterance it replies to — we explore a number of transformer-based models and found that BERT in combination with handcrafted features remains a strong baseline. We then build a multi-task learning model that jointly learns utterance-to-utterance and utterance-to-thread classification. Observing that the ground truth label (past utterance) is in the top candidates when our model makes an error, we experiment with using bipartite graphs as a post-processing step to learn how to best match a set of UOIs to past utterances. Experiments on the Ubuntu IRC dataset show that this approach has the potential to out-perform the conventional greedy approach of simply selecting the highest probability candidate for each UOI independently, indicating a promising future research direction.</abstract>
    <identifier type="citekey">zhu-etal-2021-findings</identifier>
    <location>
        <url>https://aclanthology.org/2021.alta-1.1</url>
    </location>
    <part>
        <date>2021-12</date>
        <extent unit="page">
            <start>1</start>
            <end>11</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Findings on Conversation Disentanglement
%A Zhu, Rongxin
%A Lau, Jey Han
%A Qi, Jianzhong
%Y Rahimi, Afshin
%Y Lane, William
%Y Zuccon, Guido
%S Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association
%D 2021
%8 December
%I Australasian Language Technology Association
%C Online
%F zhu-etal-2021-findings
%X Conversation disentanglement, the task to identify separate threads in conversations, is an important pre-processing step in multi-party conversational NLP applications such as conversational question answering and con-versation summarization. Framing it as a utterance-to-utterance classification problem — i.e. given an utterance of interest (UOI), find which past utterance it replies to — we explore a number of transformer-based models and found that BERT in combination with handcrafted features remains a strong baseline. We then build a multi-task learning model that jointly learns utterance-to-utterance and utterance-to-thread classification. Observing that the ground truth label (past utterance) is in the top candidates when our model makes an error, we experiment with using bipartite graphs as a post-processing step to learn how to best match a set of UOIs to past utterances. Experiments on the Ubuntu IRC dataset show that this approach has the potential to out-perform the conventional greedy approach of simply selecting the highest probability candidate for each UOI independently, indicating a promising future research direction.
%U https://aclanthology.org/2021.alta-1.1
%P 1-11

Markdown (Informal)

[Findings on Conversation Disentanglement](https://aclanthology.org/2021.alta-1.1) (Zhu et al., ALTA 2021)

• Findings on Conversation Disentanglement (Zhu et al., ALTA 2021)

ACL

• Rongxin Zhu, Jey Han Lau, and Jianzhong Qi. 2021. Findings on Conversation Disentanglement. In Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association, pages 1–11, Online. Australasian Language Technology Association.