@inproceedings{zhou-etal-2022-effectiveness,
title = "Effectiveness of {F}rench Language Models on Abstractive Dialogue Summarization Task",
author = "Zhou, Yongxin and
Portet, Fran{\c{c}}ois and
Ringeval, Fabien",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.382",
pages = "3571--3581",
abstract = "Pre-trained language models have established the state-of-the-art on various natural language processing tasks, including dialogue summarization, which allows the reader to quickly access key information from long conversations in meetings, interviews or phone calls. However, such dialogues are still difficult to handle with current models because the spontaneity of the language involves expressions that are rarely present in the corpora used for pre-training the language models. Moreover, the vast majority of the work accomplished in this field has been focused on English. In this work, we present a study on the summarization of spontaneous oral dialogues in French using several language specific pre-trained models: BARThez, and BelGPT-2, as well as multilingual pre-trained models: mBART, mBARThez, and mT5. Experiments were performed on the DECODA (Call Center) dialogue corpus whose task is to generate abstractive synopses from call center conversations between a caller and one or several agents depending on the situation. Results show that the BARThez models offer the best performance far above the previous state-of-the-art on DECODA. We further discuss the limits of such pre-trained models and the challenges that must be addressed for summarizing spontaneous dialogues.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2022-effectiveness">
<titleInfo>
<title>Effectiveness of French Language Models on Abstractive Dialogue Summarization Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongxin</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Portet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabien</namePart>
<namePart type="family">Ringeval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained language models have established the state-of-the-art on various natural language processing tasks, including dialogue summarization, which allows the reader to quickly access key information from long conversations in meetings, interviews or phone calls. However, such dialogues are still difficult to handle with current models because the spontaneity of the language involves expressions that are rarely present in the corpora used for pre-training the language models. Moreover, the vast majority of the work accomplished in this field has been focused on English. In this work, we present a study on the summarization of spontaneous oral dialogues in French using several language specific pre-trained models: BARThez, and BelGPT-2, as well as multilingual pre-trained models: mBART, mBARThez, and mT5. Experiments were performed on the DECODA (Call Center) dialogue corpus whose task is to generate abstractive synopses from call center conversations between a caller and one or several agents depending on the situation. Results show that the BARThez models offer the best performance far above the previous state-of-the-art on DECODA. We further discuss the limits of such pre-trained models and the challenges that must be addressed for summarizing spontaneous dialogues.</abstract>
<identifier type="citekey">zhou-etal-2022-effectiveness</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.382</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3571</start>
<end>3581</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effectiveness of French Language Models on Abstractive Dialogue Summarization Task
%A Zhou, Yongxin
%A Portet, François
%A Ringeval, Fabien
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F zhou-etal-2022-effectiveness
%X Pre-trained language models have established the state-of-the-art on various natural language processing tasks, including dialogue summarization, which allows the reader to quickly access key information from long conversations in meetings, interviews or phone calls. However, such dialogues are still difficult to handle with current models because the spontaneity of the language involves expressions that are rarely present in the corpora used for pre-training the language models. Moreover, the vast majority of the work accomplished in this field has been focused on English. In this work, we present a study on the summarization of spontaneous oral dialogues in French using several language specific pre-trained models: BARThez, and BelGPT-2, as well as multilingual pre-trained models: mBART, mBARThez, and mT5. Experiments were performed on the DECODA (Call Center) dialogue corpus whose task is to generate abstractive synopses from call center conversations between a caller and one or several agents depending on the situation. Results show that the BARThez models offer the best performance far above the previous state-of-the-art on DECODA. We further discuss the limits of such pre-trained models and the challenges that must be addressed for summarizing spontaneous dialogues.
%U https://aclanthology.org/2022.lrec-1.382
%P 3571-3581
Markdown (Informal)
[Effectiveness of French Language Models on Abstractive Dialogue Summarization Task](https://aclanthology.org/2022.lrec-1.382) (Zhou et al., LREC 2022)
ACL