@inproceedings{tanguy-etal-2025-embeddings,
title = "Embeddings, topic models, {LLM} : un air de famille",
author = "Tanguy, Ludovic and
Fabre, C{\'e}cile and
Hathout, Nabil and
Ho-Dac, Lydia-Mai",
editor = "Bechet, Fr{\'e}d{\'e}ric and
Chifu, Adrian-Gabriel and
Pinel-sauvagnat, Karen and
Favre, Benoit and
Maes, Eliot and
Nurbakova, Diana",
booktitle = "Actes des 32{\`e}me Conf{\'e}rence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux",
month = "6",
year = "2025",
address = "Marseille, France",
publisher = "ATALA {\textbackslash}{\textbackslash}{\&} ARIA",
url = "https://aclanthology.org/2025.jeptalnrecital-taln.18/",
pages = "295--312",
abstract = "Word embeddings, topic models, LLMs: a family affair This article presents a study on terms denoting family relationships (brother, aunt, etc.) in French using three approaches: word embeddings, topic modeling, and pre-trained language models. The first two types of representations are built from the French version of Wikipedia, while the third is derived through direct interaction with ChatGPT. The aim is to compare how these three methods represent such terms, in two main ways: by evaluating them against a structural definition of family relations (in terms of features such as gender, lineage, etc.), and by comparing the topics associated with each term. These methods reveal different modes of structuring family-related vocabulary, while also underscoring the continued necessity of corpus-based and controlled analyses to obtain reliable results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tanguy-etal-2025-embeddings">
<titleInfo>
<title>Embeddings, topic models, LLM : un air de famille</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ludovic</namePart>
<namePart type="family">Tanguy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cécile</namePart>
<namePart type="family">Fabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nabil</namePart>
<namePart type="family">Hathout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lydia-Mai</namePart>
<namePart type="family">Ho-Dac</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Actes des 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Bechet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian-Gabriel</namePart>
<namePart type="family">Chifu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Pinel-sauvagnat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoit</namePart>
<namePart type="family">Favre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliot</namePart>
<namePart type="family">Maes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Nurbakova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ATALA \textbackslash\textbackslash& ARIA</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word embeddings, topic models, LLMs: a family affair This article presents a study on terms denoting family relationships (brother, aunt, etc.) in French using three approaches: word embeddings, topic modeling, and pre-trained language models. The first two types of representations are built from the French version of Wikipedia, while the third is derived through direct interaction with ChatGPT. The aim is to compare how these three methods represent such terms, in two main ways: by evaluating them against a structural definition of family relations (in terms of features such as gender, lineage, etc.), and by comparing the topics associated with each term. These methods reveal different modes of structuring family-related vocabulary, while also underscoring the continued necessity of corpus-based and controlled analyses to obtain reliable results.</abstract>
<identifier type="citekey">tanguy-etal-2025-embeddings</identifier>
<location>
<url>https://aclanthology.org/2025.jeptalnrecital-taln.18/</url>
</location>
<part>
<date>2025-6</date>
<extent unit="page">
<start>295</start>
<end>312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Embeddings, topic models, LLM : un air de famille
%A Tanguy, Ludovic
%A Fabre, Cécile
%A Hathout, Nabil
%A Ho-Dac, Lydia-Mai
%Y Bechet, Frédéric
%Y Chifu, Adrian-Gabriel
%Y Pinel-sauvagnat, Karen
%Y Favre, Benoit
%Y Maes, Eliot
%Y Nurbakova, Diana
%S Actes des 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux
%D 2025
%8 June
%I ATALA \textbackslash\textbackslash& ARIA
%C Marseille, France
%F tanguy-etal-2025-embeddings
%X Word embeddings, topic models, LLMs: a family affair This article presents a study on terms denoting family relationships (brother, aunt, etc.) in French using three approaches: word embeddings, topic modeling, and pre-trained language models. The first two types of representations are built from the French version of Wikipedia, while the third is derived through direct interaction with ChatGPT. The aim is to compare how these three methods represent such terms, in two main ways: by evaluating them against a structural definition of family relations (in terms of features such as gender, lineage, etc.), and by comparing the topics associated with each term. These methods reveal different modes of structuring family-related vocabulary, while also underscoring the continued necessity of corpus-based and controlled analyses to obtain reliable results.
%U https://aclanthology.org/2025.jeptalnrecital-taln.18/
%P 295-312
Markdown (Informal)
[Embeddings, topic models, LLM : un air de famille](https://aclanthology.org/2025.jeptalnrecital-taln.18/) (Tanguy et al., JEP/TALN/RECITAL 2025)
ACL
- Ludovic Tanguy, Cécile Fabre, Nabil Hathout, and Lydia-Mai Ho-Dac. 2025. Embeddings, topic models, LLM : un air de famille. In Actes des 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux, pages 295–312, Marseille, France. ATALA \\& ARIA.