@inproceedings{breit-etal-2022-wic,
title = "{W}i{C}-{TSV}-de: {G}erman Word-in-Context Target-Sense-Verification Dataset and Cross-Lingual Transfer Analysis",
author = "Breit, Anna and
Revenko, Artem and
Blaschke, Narayani",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.280/",
pages = "2617--2625",
abstract = "Target Sense Verification (TSV) describes the binary disambiguation task of deciding whether the intended sense of a target word in a context corresponds to a given target sense. In this paper, we introduce WiC-TSV-de, a multi-domain dataset for German Target Sense Verification. While the training and development sets consist of domain-independent instances only, the test set contains domain-bound subsets, originating from four different domains, being Gastronomy, Medicine, Hunting, and Zoology. The domain-bound subsets incorporate adversarial examples such as in-domain ambiguous target senses and context-mixing (i.e., using the target sense in an out-of-domain context) which contribute to the challenging nature of the presented dataset. WiC-TSV-de allows for the development of sense-inventory-independent disambiguation models that can generalise their knowledge for different domain settings. By combining it with the original English WiC-TSV benchmark, we performed monolingual and cross-lingual analysis, where the evaluated baseline models were not able to solve the dataset to a satisfying degree, leaving a big gap to human performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="breit-etal-2022-wic">
<titleInfo>
<title>WiC-TSV-de: German Word-in-Context Target-Sense-Verification Dataset and Cross-Lingual Transfer Analysis</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">Narayani</namePart>
<namePart type="family">Blaschke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>Target Sense Verification (TSV) describes the binary disambiguation task of deciding whether the intended sense of a target word in a context corresponds to a given target sense. In this paper, we introduce WiC-TSV-de, a multi-domain dataset for German Target Sense Verification. While the training and development sets consist of domain-independent instances only, the test set contains domain-bound subsets, originating from four different domains, being Gastronomy, Medicine, Hunting, and Zoology. The domain-bound subsets incorporate adversarial examples such as in-domain ambiguous target senses and context-mixing (i.e., using the target sense in an out-of-domain context) which contribute to the challenging nature of the presented dataset. WiC-TSV-de allows for the development of sense-inventory-independent disambiguation models that can generalise their knowledge for different domain settings. By combining it with the original English WiC-TSV benchmark, we performed monolingual and cross-lingual analysis, where the evaluated baseline models were not able to solve the dataset to a satisfying degree, leaving a big gap to human performance.</abstract>
<identifier type="citekey">breit-etal-2022-wic</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.280/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2617</start>
<end>2625</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WiC-TSV-de: German Word-in-Context Target-Sense-Verification Dataset and Cross-Lingual Transfer Analysis
%A Breit, Anna
%A Revenko, Artem
%A Blaschke, Narayani
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F breit-etal-2022-wic
%X Target Sense Verification (TSV) describes the binary disambiguation task of deciding whether the intended sense of a target word in a context corresponds to a given target sense. In this paper, we introduce WiC-TSV-de, a multi-domain dataset for German Target Sense Verification. While the training and development sets consist of domain-independent instances only, the test set contains domain-bound subsets, originating from four different domains, being Gastronomy, Medicine, Hunting, and Zoology. The domain-bound subsets incorporate adversarial examples such as in-domain ambiguous target senses and context-mixing (i.e., using the target sense in an out-of-domain context) which contribute to the challenging nature of the presented dataset. WiC-TSV-de allows for the development of sense-inventory-independent disambiguation models that can generalise their knowledge for different domain settings. By combining it with the original English WiC-TSV benchmark, we performed monolingual and cross-lingual analysis, where the evaluated baseline models were not able to solve the dataset to a satisfying degree, leaving a big gap to human performance.
%U https://aclanthology.org/2022.lrec-1.280/
%P 2617-2625
Markdown (Informal)
[WiC-TSV-de: German Word-in-Context Target-Sense-Verification Dataset and Cross-Lingual Transfer Analysis](https://aclanthology.org/2022.lrec-1.280/) (Breit et al., LREC 2022)
ACL