@inproceedings{herman-jakubicek-2024-shadowsense,
title = "{S}hadow{S}ense: A Multi-annotated Dataset for Evaluating Word Sense Induction",
author = "Herman, Ond{\v{r}}ej and
Jakub{\'\i}{\v{c}}ek, Milo{\v{s}}",
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.1286",
pages = "14763--14769",
abstract = "In this paper we present a novel bilingual (Czech, English) dataset called ShadowSense developed for the purposes of word sense induction (WSI) evaluation. Unlike existing WSI datasets, ShadowSense is annotated by multiple annotators whose inter-annotator agreement represents key reliability score to be used for evaluation of systems automatically inducing word senses. In this paper we clarify the motivation for such an approach, describe the dataset in detail and provide evaluation of three neural WSI systems showing substantial differences compared to traditional evaluation paradigms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="herman-jakubicek-2024-shadowsense">
<titleInfo>
<title>ShadowSense: A Multi-annotated Dataset for Evaluating Word Sense Induction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Herman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miloš</namePart>
<namePart type="family">Jakubíček</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>In this paper we present a novel bilingual (Czech, English) dataset called ShadowSense developed for the purposes of word sense induction (WSI) evaluation. Unlike existing WSI datasets, ShadowSense is annotated by multiple annotators whose inter-annotator agreement represents key reliability score to be used for evaluation of systems automatically inducing word senses. In this paper we clarify the motivation for such an approach, describe the dataset in detail and provide evaluation of three neural WSI systems showing substantial differences compared to traditional evaluation paradigms.</abstract>
<identifier type="citekey">herman-jakubicek-2024-shadowsense</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1286</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14763</start>
<end>14769</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ShadowSense: A Multi-annotated Dataset for Evaluating Word Sense Induction
%A Herman, Ondřej
%A Jakubíček, Miloš
%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 herman-jakubicek-2024-shadowsense
%X In this paper we present a novel bilingual (Czech, English) dataset called ShadowSense developed for the purposes of word sense induction (WSI) evaluation. Unlike existing WSI datasets, ShadowSense is annotated by multiple annotators whose inter-annotator agreement represents key reliability score to be used for evaluation of systems automatically inducing word senses. In this paper we clarify the motivation for such an approach, describe the dataset in detail and provide evaluation of three neural WSI systems showing substantial differences compared to traditional evaluation paradigms.
%U https://aclanthology.org/2024.lrec-main.1286
%P 14763-14769
Markdown (Informal)
[ShadowSense: A Multi-annotated Dataset for Evaluating Word Sense Induction](https://aclanthology.org/2024.lrec-main.1286) (Herman & Jakubíček, LREC-COLING 2024)
ACL