Quand les questions en disent plus que les réponses : classification automatique des intentions dans les questions

This work aims to automatically detect the intents of speakers in questions asked during meals. The corpus is composed of transcripts of spontaneous oral conversations. We suggest a typology of these intents based on existing work and the corpus analysis. We implement...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Angèle Barbedette, Iris Eshkol-Taravella
Formato: article
Lenguaje:EN
FR
Publicado: Presses universitaires de Caen 2021
Materias:
Acceso en línea:https://doaj.org/article/c2b7a14a3a4e4e7a9a2616ff50d1f1a0
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:c2b7a14a3a4e4e7a9a2616ff50d1f1a0
record_format dspace
spelling oai:doaj.org-article:c2b7a14a3a4e4e7a9a2616ff50d1f1a02021-12-02T09:54:54ZQuand les questions en disent plus que les réponses : classification automatique des intentions dans les questions1963-172310.4000/discours.11359https://doaj.org/article/c2b7a14a3a4e4e7a9a2616ff50d1f1a02021-10-01T00:00:00Zhttp://journals.openedition.org/discours/11359https://doaj.org/toc/1963-1723This work aims to automatically detect the intents of speakers in questions asked during meals. The corpus is composed of transcripts of spontaneous oral conversations. We suggest a typology of these intents based on existing work and the corpus analysis. We implement a supervised automatic classification model based on annotated data and selected linguistic features, whose results and performance are evaluated and interpreted.Angèle BarbedetteIris Eshkol-TaravellaPresses universitaires de Caenarticleintention detectiondialog actspontaneous speech transcriptionsquestions classificationopinion miningmachine learningPhilology. LinguisticsP1-1091Computational linguistics. Natural language processingP98-98.5ENFRDiscours , Vol 28 (2021)
institution DOAJ
collection DOAJ
language EN
FR
topic intention detection
dialog act
spontaneous speech transcriptions
questions classification
opinion mining
machine learning
Philology. Linguistics
P1-1091
Computational linguistics. Natural language processing
P98-98.5
spellingShingle intention detection
dialog act
spontaneous speech transcriptions
questions classification
opinion mining
machine learning
Philology. Linguistics
P1-1091
Computational linguistics. Natural language processing
P98-98.5
Angèle Barbedette
Iris Eshkol-Taravella
Quand les questions en disent plus que les réponses : classification automatique des intentions dans les questions
description This work aims to automatically detect the intents of speakers in questions asked during meals. The corpus is composed of transcripts of spontaneous oral conversations. We suggest a typology of these intents based on existing work and the corpus analysis. We implement a supervised automatic classification model based on annotated data and selected linguistic features, whose results and performance are evaluated and interpreted.
format article
author Angèle Barbedette
Iris Eshkol-Taravella
author_facet Angèle Barbedette
Iris Eshkol-Taravella
author_sort Angèle Barbedette
title Quand les questions en disent plus que les réponses : classification automatique des intentions dans les questions
title_short Quand les questions en disent plus que les réponses : classification automatique des intentions dans les questions
title_full Quand les questions en disent plus que les réponses : classification automatique des intentions dans les questions
title_fullStr Quand les questions en disent plus que les réponses : classification automatique des intentions dans les questions
title_full_unstemmed Quand les questions en disent plus que les réponses : classification automatique des intentions dans les questions
title_sort quand les questions en disent plus que les réponses : classification automatique des intentions dans les questions
publisher Presses universitaires de Caen
publishDate 2021
url https://doaj.org/article/c2b7a14a3a4e4e7a9a2616ff50d1f1a0
work_keys_str_mv AT angelebarbedette quandlesquestionsendisentplusquelesreponsesclassificationautomatiquedesintentionsdanslesquestions
AT iriseshkoltaravella quandlesquestionsendisentplusquelesreponsesclassificationautomatiquedesintentionsdanslesquestions
_version_ 1718397905207820288