@inproceedings{silem-etal-2025-evaluating,
title = "Evaluating Spoken Language Features in Conversational Models: The Case of Disfluencies and Feedbacks",
author = {Silem, Oussama and
Fleig, Ma{\"i}wenn and
Blache, Philippe and
Oufaida, Houda and
Becerra-Bonache, Leonor},
editor = "B{\'e}chet, Fr{\'e}d{\'e}ric and
Lef{\`e}vre, Fabrice and
Asher, Nicholas and
Kim, Seokhwan and
Merlin, Teva",
booktitle = "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2025",
address = "Avignon, France",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.sigdial-1.23/",
pages = "285--293",
abstract = "Understanding how language is processed and represented cognitively increasingly involves the use of specialized language models. Yet, because most models are predominantly trained on written text, they struggle to reflect the characteristics of language as it naturally unfolds in spoken interaction. This gap limits their capabilities in capturing features typical of spontaneous speech, such as repetitions, feedback cues, and hesitations. In this work, we introduce linguistically motivated evaluation metrics designed to target these specific spoken-language phenomena. We apply them to analyse outputs from language models fine-tuned on spoken English and French, comparing their behaviour statistically with human dialogue corpora. Our findings highlight the value of these metrics for assessing the degree to which model-generated utterances resemble authentic human conversation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="silem-etal-2025-evaluating">
<titleInfo>
<title>Evaluating Spoken Language Features in Conversational Models: The Case of Disfluencies and Feedbacks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oussama</namePart>
<namePart type="family">Silem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maïwenn</namePart>
<namePart type="family">Fleig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Oufaida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonor</namePart>
<namePart type="family">Becerra-Bonache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<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">Fabrice</namePart>
<namePart type="family">Lefèvre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Asher</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">Teva</namePart>
<namePart type="family">Merlin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Avignon, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding how language is processed and represented cognitively increasingly involves the use of specialized language models. Yet, because most models are predominantly trained on written text, they struggle to reflect the characteristics of language as it naturally unfolds in spoken interaction. This gap limits their capabilities in capturing features typical of spontaneous speech, such as repetitions, feedback cues, and hesitations. In this work, we introduce linguistically motivated evaluation metrics designed to target these specific spoken-language phenomena. We apply them to analyse outputs from language models fine-tuned on spoken English and French, comparing their behaviour statistically with human dialogue corpora. Our findings highlight the value of these metrics for assessing the degree to which model-generated utterances resemble authentic human conversation.</abstract>
<identifier type="citekey">silem-etal-2025-evaluating</identifier>
<location>
<url>https://aclanthology.org/2025.sigdial-1.23/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>285</start>
<end>293</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Spoken Language Features in Conversational Models: The Case of Disfluencies and Feedbacks
%A Silem, Oussama
%A Fleig, Maïwenn
%A Blache, Philippe
%A Oufaida, Houda
%A Becerra-Bonache, Leonor
%Y Béchet, Frédéric
%Y Lefèvre, Fabrice
%Y Asher, Nicholas
%Y Kim, Seokhwan
%Y Merlin, Teva
%S Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2025
%8 August
%I Association for Computational Linguistics
%C Avignon, France
%F silem-etal-2025-evaluating
%X Understanding how language is processed and represented cognitively increasingly involves the use of specialized language models. Yet, because most models are predominantly trained on written text, they struggle to reflect the characteristics of language as it naturally unfolds in spoken interaction. This gap limits their capabilities in capturing features typical of spontaneous speech, such as repetitions, feedback cues, and hesitations. In this work, we introduce linguistically motivated evaluation metrics designed to target these specific spoken-language phenomena. We apply them to analyse outputs from language models fine-tuned on spoken English and French, comparing their behaviour statistically with human dialogue corpora. Our findings highlight the value of these metrics for assessing the degree to which model-generated utterances resemble authentic human conversation.
%U https://aclanthology.org/2025.sigdial-1.23/
%P 285-293
Markdown (Informal)
[Evaluating Spoken Language Features in Conversational Models: The Case of Disfluencies and Feedbacks](https://aclanthology.org/2025.sigdial-1.23/) (Silem et al., SIGDIAL 2025)
ACL