@inproceedings{millour-etal-2024-unveiling-strengths,
title = "Unveiling Strengths and Weaknesses of {NLP} Systems Based on a Rich Evaluation Corpus: The Case of {NER} in {F}rench",
author = "Millour, Alice and
Dupont, Yoann and
Fort, Karen and
Duignan, Liam",
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.1495",
pages = "17217--17224",
abstract = "Named Entity Recognition (NER) is an applicative task for which annotation schemes vary. To compare the performance of systems which tagsets differ in precision and coverage, it is necessary to assess (i) the comparability of their annotation schemes and (ii) the individual adequacy of the latter to a common annotation scheme. What is more, and given the lack of robustness of some tools towards textual variation, we cannot expect an evaluation led on an homogeneous corpus with low-coverage to provide a reliable prediction of the actual tools performance. To tackle both these limitations in evaluation, we provide a gold corpus for French covering 6 textual genres and annotated with a rich tagset that enables comparison with multiple annotation schemes. We use the flexibility of this gold corpus to provide both: (i) an individual evaluation of four heterogeneous NER systems on their target tagsets, (ii) a comparison of their performance on a common scheme. This rich evaluation framework enables a fair comparison of NER systems across textual genres and annotation schemes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="millour-etal-2024-unveiling-strengths">
<titleInfo>
<title>Unveiling Strengths and Weaknesses of NLP Systems Based on a Rich Evaluation Corpus: The Case of NER in French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Millour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoann</namePart>
<namePart type="family">Dupont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Fort</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liam</namePart>
<namePart type="family">Duignan</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>Named Entity Recognition (NER) is an applicative task for which annotation schemes vary. To compare the performance of systems which tagsets differ in precision and coverage, it is necessary to assess (i) the comparability of their annotation schemes and (ii) the individual adequacy of the latter to a common annotation scheme. What is more, and given the lack of robustness of some tools towards textual variation, we cannot expect an evaluation led on an homogeneous corpus with low-coverage to provide a reliable prediction of the actual tools performance. To tackle both these limitations in evaluation, we provide a gold corpus for French covering 6 textual genres and annotated with a rich tagset that enables comparison with multiple annotation schemes. We use the flexibility of this gold corpus to provide both: (i) an individual evaluation of four heterogeneous NER systems on their target tagsets, (ii) a comparison of their performance on a common scheme. This rich evaluation framework enables a fair comparison of NER systems across textual genres and annotation schemes.</abstract>
<identifier type="citekey">millour-etal-2024-unveiling-strengths</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1495</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17217</start>
<end>17224</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unveiling Strengths and Weaknesses of NLP Systems Based on a Rich Evaluation Corpus: The Case of NER in French
%A Millour, Alice
%A Dupont, Yoann
%A Fort, Karen
%A Duignan, Liam
%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 millour-etal-2024-unveiling-strengths
%X Named Entity Recognition (NER) is an applicative task for which annotation schemes vary. To compare the performance of systems which tagsets differ in precision and coverage, it is necessary to assess (i) the comparability of their annotation schemes and (ii) the individual adequacy of the latter to a common annotation scheme. What is more, and given the lack of robustness of some tools towards textual variation, we cannot expect an evaluation led on an homogeneous corpus with low-coverage to provide a reliable prediction of the actual tools performance. To tackle both these limitations in evaluation, we provide a gold corpus for French covering 6 textual genres and annotated with a rich tagset that enables comparison with multiple annotation schemes. We use the flexibility of this gold corpus to provide both: (i) an individual evaluation of four heterogeneous NER systems on their target tagsets, (ii) a comparison of their performance on a common scheme. This rich evaluation framework enables a fair comparison of NER systems across textual genres and annotation schemes.
%U https://aclanthology.org/2024.lrec-main.1495
%P 17217-17224
Markdown (Informal)
[Unveiling Strengths and Weaknesses of NLP Systems Based on a Rich Evaluation Corpus: The Case of NER in French](https://aclanthology.org/2024.lrec-main.1495) (Millour et al., LREC-COLING 2024)
ACL