@inproceedings{breit-etal-2021-wic,
title = "{WiC-TSV}: {A}n Evaluation Benchmark for Target Sense Verification of Words in Context",
author = "Breit, Anna and
Revenko, Artem and
Rezaee, Kiamehr and
Pilehvar, Mohammad Taher and
Camacho-Collados, Jose",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.140",
doi = "10.18653/v1/2021.eacl-main.140",
pages = "1635--1645",
abstract = "We present WiC-TSV, a new multi-domain evaluation benchmark for Word Sense Disambiguation. More specifically, we introduce a framework for Target Sense Verification of Words in Context which grounds its uniqueness in the formulation as binary classification task thus being independent of external sense inventories, and the coverage of various domains. This makes the dataset highly flexible for the evaluation of a diverse set of models and systems in and across domains. WiC-TSV provides three different evaluation settings, depending on the input signals provided to the model. We set baseline performance on the dataset using state-of-the-art language models. Experimental results show that even though these models can perform decently on the task, there remains a gap between machine and human performance, especially in out-of-domain settings. WiC-TSV data is available at \url{https://competitions.codalab.org/competitions/23683}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="breit-etal-2021-wic">
<titleInfo>
<title>WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Breit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Revenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiamehr</namePart>
<namePart type="family">Rezaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present WiC-TSV, a new multi-domain evaluation benchmark for Word Sense Disambiguation. More specifically, we introduce a framework for Target Sense Verification of Words in Context which grounds its uniqueness in the formulation as binary classification task thus being independent of external sense inventories, and the coverage of various domains. This makes the dataset highly flexible for the evaluation of a diverse set of models and systems in and across domains. WiC-TSV provides three different evaluation settings, depending on the input signals provided to the model. We set baseline performance on the dataset using state-of-the-art language models. Experimental results show that even though these models can perform decently on the task, there remains a gap between machine and human performance, especially in out-of-domain settings. WiC-TSV data is available at https://competitions.codalab.org/competitions/23683.</abstract>
<identifier type="citekey">breit-etal-2021-wic</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.140</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.140</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1635</start>
<end>1645</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context
%A Breit, Anna
%A Revenko, Artem
%A Rezaee, Kiamehr
%A Pilehvar, Mohammad Taher
%A Camacho-Collados, Jose
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F breit-etal-2021-wic
%X We present WiC-TSV, a new multi-domain evaluation benchmark for Word Sense Disambiguation. More specifically, we introduce a framework for Target Sense Verification of Words in Context which grounds its uniqueness in the formulation as binary classification task thus being independent of external sense inventories, and the coverage of various domains. This makes the dataset highly flexible for the evaluation of a diverse set of models and systems in and across domains. WiC-TSV provides three different evaluation settings, depending on the input signals provided to the model. We set baseline performance on the dataset using state-of-the-art language models. Experimental results show that even though these models can perform decently on the task, there remains a gap between machine and human performance, especially in out-of-domain settings. WiC-TSV data is available at https://competitions.codalab.org/competitions/23683.
%R 10.18653/v1/2021.eacl-main.140
%U https://aclanthology.org/2021.eacl-main.140
%U https://doi.org/10.18653/v1/2021.eacl-main.140
%P 1635-1645
Markdown (Informal)
[WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context](https://aclanthology.org/2021.eacl-main.140) (Breit et al., EACL 2021)
ACL