@inproceedings{skandalis-etal-2024-new-datasets,
title = "New Datasets for Automatic Detection of Textual Entailment and of Contradictions between Sentences in {F}rench",
author = "Skandalis, Maximos and
Moot, Richard and
Retor{\'e}, Christian and
Robillard, Simon",
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.1065",
pages = "12173--12186",
abstract = "This paper introduces DACCORD, an original dataset in French for automatic detection of contradictions between sentences. It also presents new, manually translated versions of two datasets, namely the well known dataset RTE3 and the recent dataset GQNLI, from English to French, for the task of natural language inference / recognising textual entailment, which is a sentence-pair classification task. These datasets help increase the admittedly limited number of datasets in French available for these tasks. DACCORD consists of 1034 pairs of sentences and is the first dataset exclusively dedicated to this task and covering among others the topic of the Russian invasion in Ukraine. RTE3-FR contains 800 examples for each of its validation and test subsets, while GQNLI-FR is composed of 300 pairs of sentences and focuses specifically on the use of generalised quantifiers. Our experiments on these datasets show that they are more challenging than the two already existing datasets for the mainstream NLI task in French (XNLI, FraCaS). For languages other than English, most deep learning models for NLI tasks currently have only XNLI available as a training set. Additional datasets, such as ours for French, could permit different training and evaluation strategies, producing more robust results and reducing the inevitable biases present in any single dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skandalis-etal-2024-new-datasets">
<titleInfo>
<title>New Datasets for Automatic Detection of Textual Entailment and of Contradictions between Sentences in French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maximos</namePart>
<namePart type="family">Skandalis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Moot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Retoré</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Robillard</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>This paper introduces DACCORD, an original dataset in French for automatic detection of contradictions between sentences. It also presents new, manually translated versions of two datasets, namely the well known dataset RTE3 and the recent dataset GQNLI, from English to French, for the task of natural language inference / recognising textual entailment, which is a sentence-pair classification task. These datasets help increase the admittedly limited number of datasets in French available for these tasks. DACCORD consists of 1034 pairs of sentences and is the first dataset exclusively dedicated to this task and covering among others the topic of the Russian invasion in Ukraine. RTE3-FR contains 800 examples for each of its validation and test subsets, while GQNLI-FR is composed of 300 pairs of sentences and focuses specifically on the use of generalised quantifiers. Our experiments on these datasets show that they are more challenging than the two already existing datasets for the mainstream NLI task in French (XNLI, FraCaS). For languages other than English, most deep learning models for NLI tasks currently have only XNLI available as a training set. Additional datasets, such as ours for French, could permit different training and evaluation strategies, producing more robust results and reducing the inevitable biases present in any single dataset.</abstract>
<identifier type="citekey">skandalis-etal-2024-new-datasets</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1065</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12173</start>
<end>12186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T New Datasets for Automatic Detection of Textual Entailment and of Contradictions between Sentences in French
%A Skandalis, Maximos
%A Moot, Richard
%A Retoré, Christian
%A Robillard, Simon
%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 skandalis-etal-2024-new-datasets
%X This paper introduces DACCORD, an original dataset in French for automatic detection of contradictions between sentences. It also presents new, manually translated versions of two datasets, namely the well known dataset RTE3 and the recent dataset GQNLI, from English to French, for the task of natural language inference / recognising textual entailment, which is a sentence-pair classification task. These datasets help increase the admittedly limited number of datasets in French available for these tasks. DACCORD consists of 1034 pairs of sentences and is the first dataset exclusively dedicated to this task and covering among others the topic of the Russian invasion in Ukraine. RTE3-FR contains 800 examples for each of its validation and test subsets, while GQNLI-FR is composed of 300 pairs of sentences and focuses specifically on the use of generalised quantifiers. Our experiments on these datasets show that they are more challenging than the two already existing datasets for the mainstream NLI task in French (XNLI, FraCaS). For languages other than English, most deep learning models for NLI tasks currently have only XNLI available as a training set. Additional datasets, such as ours for French, could permit different training and evaluation strategies, producing more robust results and reducing the inevitable biases present in any single dataset.
%U https://aclanthology.org/2024.lrec-main.1065
%P 12173-12186
Markdown (Informal)
[New Datasets for Automatic Detection of Textual Entailment and of Contradictions between Sentences in French](https://aclanthology.org/2024.lrec-main.1065) (Skandalis et al., LREC-COLING 2024)
ACL