@inproceedings{kumar-dusek-2024-leeets,
title = "{LEEET}s-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems",
author = "Kumar, Nalin and
Dusek, Ondrej",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.46",
doi = "10.18653/v1/2024.findings-naacl.46",
pages = "727--735",
abstract = "Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been shown to produce a more natural user experience, most dialogue systems do not have any provisions for it. In this work, we introduce methods for achieving dialogue entrainment in a GPT-2-based end-to-end task-oriented dialogue system through the utilization of shared vocabulary. We experiment with training instance weighting, entrainment-specific loss, and additional conditioning to generate responses that align with the user. We demonstrate that all three approaches produce significantly better entrainment than the base, non-entrainment-optimized model, as confirmed by both automated and manual evaluation metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-dusek-2024-leeets">
<titleInfo>
<title>LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nalin</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Dusek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been shown to produce a more natural user experience, most dialogue systems do not have any provisions for it. In this work, we introduce methods for achieving dialogue entrainment in a GPT-2-based end-to-end task-oriented dialogue system through the utilization of shared vocabulary. We experiment with training instance weighting, entrainment-specific loss, and additional conditioning to generate responses that align with the user. We demonstrate that all three approaches produce significantly better entrainment than the base, non-entrainment-optimized model, as confirmed by both automated and manual evaluation metrics.</abstract>
<identifier type="citekey">kumar-dusek-2024-leeets</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.46</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.46</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>727</start>
<end>735</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems
%A Kumar, Nalin
%A Dusek, Ondrej
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F kumar-dusek-2024-leeets
%X Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While entrainment has been shown to produce a more natural user experience, most dialogue systems do not have any provisions for it. In this work, we introduce methods for achieving dialogue entrainment in a GPT-2-based end-to-end task-oriented dialogue system through the utilization of shared vocabulary. We experiment with training instance weighting, entrainment-specific loss, and additional conditioning to generate responses that align with the user. We demonstrate that all three approaches produce significantly better entrainment than the base, non-entrainment-optimized model, as confirmed by both automated and manual evaluation metrics.
%R 10.18653/v1/2024.findings-naacl.46
%U https://aclanthology.org/2024.findings-naacl.46
%U https://doi.org/10.18653/v1/2024.findings-naacl.46
%P 727-735
Markdown (Informal)
[LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems](https://aclanthology.org/2024.findings-naacl.46) (Kumar & Dusek, Findings 2024)
ACL