@inproceedings{labruna-magnini-2023-addressing,
title = "Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation",
author = "Labruna, Tiziano and
Magnini, Bernardo",
editor = "Bassignana, Elisa and
Lindemann, Matthias and
Petit, Alban",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-srw.16",
doi = "10.18653/v1/2023.eacl-srw.16",
pages = "149--158",
abstract = "Recent task-oriented dialogue systems are trained on annotated dialogues, which, in turn, reflect certain domain information (e.g., restaurants or hotels in a given region). However, when such domain knowledge changes (e.g., new restaurants open), the initial dialogue model may become obsolete, decreasing the overall performance of the system. Through a number of experiments, we show, for instance, that adding 50{\%} of new slot-values reduces of about 55{\%} the dialogue state-tracker performance. In light of such evidence, we suggest that automatic adaptation of training dialogues is a valuable option for re-training obsolete models. We experimented with a dialogue adaptation approach based on fine-tuning a generative language model on domain changes, showing that a significant reduction of performance decrease can be obtained.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="labruna-magnini-2023-addressing">
<titleInfo>
<title>Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tiziano</namePart>
<namePart type="family">Labruna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernardo</namePart>
<namePart type="family">Magnini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Bassignana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Lindemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alban</namePart>
<namePart type="family">Petit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent task-oriented dialogue systems are trained on annotated dialogues, which, in turn, reflect certain domain information (e.g., restaurants or hotels in a given region). However, when such domain knowledge changes (e.g., new restaurants open), the initial dialogue model may become obsolete, decreasing the overall performance of the system. Through a number of experiments, we show, for instance, that adding 50% of new slot-values reduces of about 55% the dialogue state-tracker performance. In light of such evidence, we suggest that automatic adaptation of training dialogues is a valuable option for re-training obsolete models. We experimented with a dialogue adaptation approach based on fine-tuning a generative language model on domain changes, showing that a significant reduction of performance decrease can be obtained.</abstract>
<identifier type="citekey">labruna-magnini-2023-addressing</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-srw.16</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-srw.16</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>149</start>
<end>158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation
%A Labruna, Tiziano
%A Magnini, Bernardo
%Y Bassignana, Elisa
%Y Lindemann, Matthias
%Y Petit, Alban
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F labruna-magnini-2023-addressing
%X Recent task-oriented dialogue systems are trained on annotated dialogues, which, in turn, reflect certain domain information (e.g., restaurants or hotels in a given region). However, when such domain knowledge changes (e.g., new restaurants open), the initial dialogue model may become obsolete, decreasing the overall performance of the system. Through a number of experiments, we show, for instance, that adding 50% of new slot-values reduces of about 55% the dialogue state-tracker performance. In light of such evidence, we suggest that automatic adaptation of training dialogues is a valuable option for re-training obsolete models. We experimented with a dialogue adaptation approach based on fine-tuning a generative language model on domain changes, showing that a significant reduction of performance decrease can be obtained.
%R 10.18653/v1/2023.eacl-srw.16
%U https://aclanthology.org/2023.eacl-srw.16
%U https://doi.org/10.18653/v1/2023.eacl-srw.16
%P 149-158
Markdown (Informal)
[Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation](https://aclanthology.org/2023.eacl-srw.16) (Labruna & Magnini, EACL 2023)
ACL