@inproceedings{bernier-colborne-langlais-2020-hardeval,
title = "{H}ard{E}val: Focusing on Challenging Tokens to Assess Robustness of {NER}",
author = "Bernier-Colborne, Gabriel and
Langlais, Phillippe",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.211",
pages = "1704--1711",
abstract = "To assess the robustness of NER systems, we propose an evaluation method that focuses on subsets of tokens that represent specific sources of errors: unknown words and label shift or ambiguity. These subsets provide a system-agnostic basis for evaluating specific sources of NER errors and assessing room for improvement in terms of robustness. We analyze these subsets of challenging tokens in two widely-used NER benchmarks, then exploit them to evaluate NER systems in both in-domain and out-of-domain settings. Results show that these challenging tokens explain the majority of errors made by modern NER systems, although they represent only a small fraction of test tokens. They also indicate that label shift is harder to deal with than unknown words, and that there is much more room for improvement than the standard NER evaluation procedure would suggest. We hope this work will encourage NLP researchers to adopt rigorous and meaningful evaluation methods, and will help them develop more robust models.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bernier-colborne-langlais-2020-hardeval">
<titleInfo>
<title>HardEval: Focusing on Challenging Tokens to Assess Robustness of NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Bernier-Colborne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phillippe</namePart>
<namePart type="family">Langlais</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>To assess the robustness of NER systems, we propose an evaluation method that focuses on subsets of tokens that represent specific sources of errors: unknown words and label shift or ambiguity. These subsets provide a system-agnostic basis for evaluating specific sources of NER errors and assessing room for improvement in terms of robustness. We analyze these subsets of challenging tokens in two widely-used NER benchmarks, then exploit them to evaluate NER systems in both in-domain and out-of-domain settings. Results show that these challenging tokens explain the majority of errors made by modern NER systems, although they represent only a small fraction of test tokens. They also indicate that label shift is harder to deal with than unknown words, and that there is much more room for improvement than the standard NER evaluation procedure would suggest. We hope this work will encourage NLP researchers to adopt rigorous and meaningful evaluation methods, and will help them develop more robust models.</abstract>
<identifier type="citekey">bernier-colborne-langlais-2020-hardeval</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.211</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1704</start>
<end>1711</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HardEval: Focusing on Challenging Tokens to Assess Robustness of NER
%A Bernier-Colborne, Gabriel
%A Langlais, Phillippe
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F bernier-colborne-langlais-2020-hardeval
%X To assess the robustness of NER systems, we propose an evaluation method that focuses on subsets of tokens that represent specific sources of errors: unknown words and label shift or ambiguity. These subsets provide a system-agnostic basis for evaluating specific sources of NER errors and assessing room for improvement in terms of robustness. We analyze these subsets of challenging tokens in two widely-used NER benchmarks, then exploit them to evaluate NER systems in both in-domain and out-of-domain settings. Results show that these challenging tokens explain the majority of errors made by modern NER systems, although they represent only a small fraction of test tokens. They also indicate that label shift is harder to deal with than unknown words, and that there is much more room for improvement than the standard NER evaluation procedure would suggest. We hope this work will encourage NLP researchers to adopt rigorous and meaningful evaluation methods, and will help them develop more robust models.
%U https://aclanthology.org/2020.lrec-1.211
%P 1704-1711
Markdown (Informal)
[HardEval: Focusing on Challenging Tokens to Assess Robustness of NER](https://aclanthology.org/2020.lrec-1.211) (Bernier-Colborne & Langlais, LREC 2020)
ACL