@inproceedings{maru-etal-2022-nibbling,
title = "{N}ibbling at the Hard Core of {W}ord {S}ense {D}isambiguation",
author = "Maru, Marco and
Conia, Simone and
Bevilacqua, Michele and
Navigli, Roberto",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.324",
doi = "10.18653/v1/2022.acl-long.324",
pages = "4724--4737",
abstract = "With state-of-the-art systems having finally attained estimated human performance, Word Sense Disambiguation (WSD) has now joined the array of Natural Language Processing tasks that have seemingly been solved, thanks to the vast amounts of knowledge encoded into Transformer-based pre-trained language models. And yet, if we look below the surface of raw figures, it is easy to realize that current approaches still make trivial mistakes that a human would never make. In this work, we provide evidence showing why the F1 score metric should not simply be taken at face value and present an exhaustive analysis of the errors that seven of the most representative state-of-the-art systems for English all-words WSD make on traditional evaluation benchmarks. In addition, we produce and release a collection of test sets featuring (a) an amended version of the standard evaluation benchmark that fixes its lexical and semantic inaccuracies, (b) 42D, a challenge set devised to assess the resilience of systems with respect to least frequent word senses and senses not seen at training time, and (c) hardEN, a challenge set made up solely of instances which none of the investigated state-of-the-art systems can solve. We make all of the test sets and model predictions available to the research community at \url{https://github.com/SapienzaNLP/wsd-hard-benchmark}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maru-etal-2022-nibbling">
<titleInfo>
<title>Nibbling at the Hard Core of Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Maru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Conia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Bevilacqua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With state-of-the-art systems having finally attained estimated human performance, Word Sense Disambiguation (WSD) has now joined the array of Natural Language Processing tasks that have seemingly been solved, thanks to the vast amounts of knowledge encoded into Transformer-based pre-trained language models. And yet, if we look below the surface of raw figures, it is easy to realize that current approaches still make trivial mistakes that a human would never make. In this work, we provide evidence showing why the F1 score metric should not simply be taken at face value and present an exhaustive analysis of the errors that seven of the most representative state-of-the-art systems for English all-words WSD make on traditional evaluation benchmarks. In addition, we produce and release a collection of test sets featuring (a) an amended version of the standard evaluation benchmark that fixes its lexical and semantic inaccuracies, (b) 42D, a challenge set devised to assess the resilience of systems with respect to least frequent word senses and senses not seen at training time, and (c) hardEN, a challenge set made up solely of instances which none of the investigated state-of-the-art systems can solve. We make all of the test sets and model predictions available to the research community at https://github.com/SapienzaNLP/wsd-hard-benchmark.</abstract>
<identifier type="citekey">maru-etal-2022-nibbling</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.324</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.324</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>4724</start>
<end>4737</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Nibbling at the Hard Core of Word Sense Disambiguation
%A Maru, Marco
%A Conia, Simone
%A Bevilacqua, Michele
%A Navigli, Roberto
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F maru-etal-2022-nibbling
%X With state-of-the-art systems having finally attained estimated human performance, Word Sense Disambiguation (WSD) has now joined the array of Natural Language Processing tasks that have seemingly been solved, thanks to the vast amounts of knowledge encoded into Transformer-based pre-trained language models. And yet, if we look below the surface of raw figures, it is easy to realize that current approaches still make trivial mistakes that a human would never make. In this work, we provide evidence showing why the F1 score metric should not simply be taken at face value and present an exhaustive analysis of the errors that seven of the most representative state-of-the-art systems for English all-words WSD make on traditional evaluation benchmarks. In addition, we produce and release a collection of test sets featuring (a) an amended version of the standard evaluation benchmark that fixes its lexical and semantic inaccuracies, (b) 42D, a challenge set devised to assess the resilience of systems with respect to least frequent word senses and senses not seen at training time, and (c) hardEN, a challenge set made up solely of instances which none of the investigated state-of-the-art systems can solve. We make all of the test sets and model predictions available to the research community at https://github.com/SapienzaNLP/wsd-hard-benchmark.
%R 10.18653/v1/2022.acl-long.324
%U https://aclanthology.org/2022.acl-long.324
%U https://doi.org/10.18653/v1/2022.acl-long.324
%P 4724-4737
Markdown (Informal)
[Nibbling at the Hard Core of Word Sense Disambiguation](https://aclanthology.org/2022.acl-long.324) (Maru et al., ACL 2022)
ACL
- Marco Maru, Simone Conia, Michele Bevilacqua, and Roberto Navigli. 2022. Nibbling at the Hard Core of Word Sense Disambiguation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4724–4737, Dublin, Ireland. Association for Computational Linguistics.