@inproceedings{su-zhou-2022-speaker,
title = "Speaker Clustering in Textual Dialogue with Pairwise Utterance Relation and Cross-corpus Dialogue Act Supervision",
author = "Su, Zhihua and
Zhou, Qiang",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.61",
pages = "734--744",
abstract = "We propose a speaker clustering model for textual dialogues, which groups the utterances of a multi-party dialogue without speaker annotations, so that the actual speakers are identical inside each cluster. We find that, without knowing the speakers, the interactions between utterances are still implied in the text, which suggest the relations between speakers. In this work, we model the semantic content of utterance with a pre-trained language model, and the relations between speakers with an utterance-level pairwise matrix. The semantic content representation can be further instructed by cross-corpus dialogue act modeling. The speaker labels are finally generated by spectral clustering. Experiments show that our model outperforms the sequence classification baseline, and benefits from the auxiliary dialogue act classification task. We also discuss the detail of determining the number of speakers (clusters), eliminating the interference caused by semantic similarity, and the impact of utterance distance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="su-zhou-2022-speaker">
<titleInfo>
<title>Speaker Clustering in Textual Dialogue with Pairwise Utterance Relation and Cross-corpus Dialogue Act Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihua</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a speaker clustering model for textual dialogues, which groups the utterances of a multi-party dialogue without speaker annotations, so that the actual speakers are identical inside each cluster. We find that, without knowing the speakers, the interactions between utterances are still implied in the text, which suggest the relations between speakers. In this work, we model the semantic content of utterance with a pre-trained language model, and the relations between speakers with an utterance-level pairwise matrix. The semantic content representation can be further instructed by cross-corpus dialogue act modeling. The speaker labels are finally generated by spectral clustering. Experiments show that our model outperforms the sequence classification baseline, and benefits from the auxiliary dialogue act classification task. We also discuss the detail of determining the number of speakers (clusters), eliminating the interference caused by semantic similarity, and the impact of utterance distance.</abstract>
<identifier type="citekey">su-zhou-2022-speaker</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.61</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>734</start>
<end>744</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speaker Clustering in Textual Dialogue with Pairwise Utterance Relation and Cross-corpus Dialogue Act Supervision
%A Su, Zhihua
%A Zhou, Qiang
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F su-zhou-2022-speaker
%X We propose a speaker clustering model for textual dialogues, which groups the utterances of a multi-party dialogue without speaker annotations, so that the actual speakers are identical inside each cluster. We find that, without knowing the speakers, the interactions between utterances are still implied in the text, which suggest the relations between speakers. In this work, we model the semantic content of utterance with a pre-trained language model, and the relations between speakers with an utterance-level pairwise matrix. The semantic content representation can be further instructed by cross-corpus dialogue act modeling. The speaker labels are finally generated by spectral clustering. Experiments show that our model outperforms the sequence classification baseline, and benefits from the auxiliary dialogue act classification task. We also discuss the detail of determining the number of speakers (clusters), eliminating the interference caused by semantic similarity, and the impact of utterance distance.
%U https://aclanthology.org/2022.coling-1.61
%P 734-744
Markdown (Informal)
[Speaker Clustering in Textual Dialogue with Pairwise Utterance Relation and Cross-corpus Dialogue Act Supervision](https://aclanthology.org/2022.coling-1.61) (Su & Zhou, COLING 2022)
ACL