@inproceedings{xie-etal-2022-view,
title = "View Dialogue in 2{D}: A Two-stream Model in Time-speaker Perspective for Dialogue Summarization and beyond",
author = "Xie, Keli and
He, Dongchen and
Zhuang, Jiaxin and
Lu, Siyuan and
Wang, Zhongfeng",
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-1.531",
pages = "6075--6088",
abstract = "Existing works on dialogue summarization often follow the common practice in document summarization and view the dialogue, which comprises utterances of different speakers, as a single utterance stream ordered by time. However, this single-stream approach without specific attention to the speaker-centered points has limitations in fully understanding the dialogue. To better capture the dialogue information, we propose a 2D view of dialogue based on a time-speaker perspective, where the time and speaker streams of dialogue can be obtained as strengthened input. Based on this 2D view, we present an effective two-stream model called ATM to combine the two streams. Extensive experiments on various summarization datasets demonstrate that ATM significantly surpasses other models regarding diverse metrics and beats the state-of-the-art models on the QMSum dataset in ROUGE scores. Besides, ATM achieves great improvements in summary faithfulness and human evaluation. Moreover, results on machine reading comprehension datasets show the generalization ability of the proposed methods and shed light on other dialogue-based tasks. Our code will be publicly available online.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2022-view">
<titleInfo>
<title>View Dialogue in 2D: A Two-stream Model in Time-speaker Perspective for Dialogue Summarization and beyond</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keli</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongchen</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyuan</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongfeng</namePart>
<namePart type="family">Wang</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>Existing works on dialogue summarization often follow the common practice in document summarization and view the dialogue, which comprises utterances of different speakers, as a single utterance stream ordered by time. However, this single-stream approach without specific attention to the speaker-centered points has limitations in fully understanding the dialogue. To better capture the dialogue information, we propose a 2D view of dialogue based on a time-speaker perspective, where the time and speaker streams of dialogue can be obtained as strengthened input. Based on this 2D view, we present an effective two-stream model called ATM to combine the two streams. Extensive experiments on various summarization datasets demonstrate that ATM significantly surpasses other models regarding diverse metrics and beats the state-of-the-art models on the QMSum dataset in ROUGE scores. Besides, ATM achieves great improvements in summary faithfulness and human evaluation. Moreover, results on machine reading comprehension datasets show the generalization ability of the proposed methods and shed light on other dialogue-based tasks. Our code will be publicly available online.</abstract>
<identifier type="citekey">xie-etal-2022-view</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.531</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>6075</start>
<end>6088</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T View Dialogue in 2D: A Two-stream Model in Time-speaker Perspective for Dialogue Summarization and beyond
%A Xie, Keli
%A He, Dongchen
%A Zhuang, Jiaxin
%A Lu, Siyuan
%A Wang, Zhongfeng
%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 xie-etal-2022-view
%X Existing works on dialogue summarization often follow the common practice in document summarization and view the dialogue, which comprises utterances of different speakers, as a single utterance stream ordered by time. However, this single-stream approach without specific attention to the speaker-centered points has limitations in fully understanding the dialogue. To better capture the dialogue information, we propose a 2D view of dialogue based on a time-speaker perspective, where the time and speaker streams of dialogue can be obtained as strengthened input. Based on this 2D view, we present an effective two-stream model called ATM to combine the two streams. Extensive experiments on various summarization datasets demonstrate that ATM significantly surpasses other models regarding diverse metrics and beats the state-of-the-art models on the QMSum dataset in ROUGE scores. Besides, ATM achieves great improvements in summary faithfulness and human evaluation. Moreover, results on machine reading comprehension datasets show the generalization ability of the proposed methods and shed light on other dialogue-based tasks. Our code will be publicly available online.
%U https://aclanthology.org/2022.coling-1.531
%P 6075-6088
Markdown (Informal)
[View Dialogue in 2D: A Two-stream Model in Time-speaker Perspective for Dialogue Summarization and beyond](https://aclanthology.org/2022.coling-1.531) (Xie et al., COLING 2022)
ACL