@inproceedings{alavoine-etal-2024-new-semantic,
title = "New Semantic Task for the {F}rench Spoken Language Understanding {MEDIA} Benchmark",
author = {Alavoine, Nad{\`e}ge and
Laperri{\`e}re, Ga{\"e}lle and
Servan, Christophe and
Ghannay, Sahar and
Rosset, Sophie},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1070",
pages = "12227--12246",
abstract = "Intent classification and slot-filling are essential tasks of Spoken Language Understanding (SLU). In most SLU systems, those tasks are realized by independent modules, but for about fifteen years, models achieving both of them jointly and exploiting their mutual enhancement have been proposed. A multilingual module using a joint model was envisioned to create a touristic dialogue system for a European project, HumanE-AI-Net. A combination of multiple datasets, including the MEDIA dataset, was suggested for training this joint model. The MEDIA SLU dataset is a French dataset distributed since 2005 by ELRA, mainly used by the French research community and free for academic research since 2020. Unfortunately, it is annotated only in slots but not intents. An enhanced version of MEDIA annotated with intents has been built to extend its use to more tasks and use cases. This paper presents the semi-automatic methodology used to obtain this enhanced version. In addition, we present the first results of SLU experiments on this enhanced dataset using joint models for intent classification and slot-filling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alavoine-etal-2024-new-semantic">
<titleInfo>
<title>New Semantic Task for the French Spoken Language Understanding MEDIA Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nadège</namePart>
<namePart type="family">Alavoine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaëlle</namePart>
<namePart type="family">Laperrière</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Servan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Ghannay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Rosset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Intent classification and slot-filling are essential tasks of Spoken Language Understanding (SLU). In most SLU systems, those tasks are realized by independent modules, but for about fifteen years, models achieving both of them jointly and exploiting their mutual enhancement have been proposed. A multilingual module using a joint model was envisioned to create a touristic dialogue system for a European project, HumanE-AI-Net. A combination of multiple datasets, including the MEDIA dataset, was suggested for training this joint model. The MEDIA SLU dataset is a French dataset distributed since 2005 by ELRA, mainly used by the French research community and free for academic research since 2020. Unfortunately, it is annotated only in slots but not intents. An enhanced version of MEDIA annotated with intents has been built to extend its use to more tasks and use cases. This paper presents the semi-automatic methodology used to obtain this enhanced version. In addition, we present the first results of SLU experiments on this enhanced dataset using joint models for intent classification and slot-filling.</abstract>
<identifier type="citekey">alavoine-etal-2024-new-semantic</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1070</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12227</start>
<end>12246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T New Semantic Task for the French Spoken Language Understanding MEDIA Benchmark
%A Alavoine, Nadège
%A Laperrière, Gaëlle
%A Servan, Christophe
%A Ghannay, Sahar
%A Rosset, Sophie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F alavoine-etal-2024-new-semantic
%X Intent classification and slot-filling are essential tasks of Spoken Language Understanding (SLU). In most SLU systems, those tasks are realized by independent modules, but for about fifteen years, models achieving both of them jointly and exploiting their mutual enhancement have been proposed. A multilingual module using a joint model was envisioned to create a touristic dialogue system for a European project, HumanE-AI-Net. A combination of multiple datasets, including the MEDIA dataset, was suggested for training this joint model. The MEDIA SLU dataset is a French dataset distributed since 2005 by ELRA, mainly used by the French research community and free for academic research since 2020. Unfortunately, it is annotated only in slots but not intents. An enhanced version of MEDIA annotated with intents has been built to extend its use to more tasks and use cases. This paper presents the semi-automatic methodology used to obtain this enhanced version. In addition, we present the first results of SLU experiments on this enhanced dataset using joint models for intent classification and slot-filling.
%U https://aclanthology.org/2024.lrec-main.1070
%P 12227-12246
Markdown (Informal)
[New Semantic Task for the French Spoken Language Understanding MEDIA Benchmark](https://aclanthology.org/2024.lrec-main.1070) (Alavoine et al., LREC-COLING 2024)
ACL