@inproceedings{alagic-snajder-2016-cro36wsd,
title = "{C}ro36{WSD}: A Lexical Sample for {C}roatian Word Sense Disambiguation",
author = "Alagi{\'c}, Domagoj and
{\v{S}}najder, Jan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1267",
pages = "1689--1694",
abstract = "We introduce Cro36WSD, a freely-available medium-sized lexical sample for Croatian word sense disambiguation (WSD).Cro36WSD comprises 36 words: 12 adjectives, 12 nouns, and 12 verbs, balanced across both frequency bands and polysemy levels. We adopt the multi-label annotation scheme in the hope of lessening the drawbacks of discrete sense inventories and obtaining more realistic annotations from human experts. Sense-annotated data is collected through multiple annotation rounds to ensure high-quality annotations: with a 115 person-hours effort we reached an inter-annotator agreement score of 0.877. We analyze the obtained data and perform a correlation analysis between several relevant variables, including word frequency, number of senses, sense distribution skewness, average annotation time, and the observed inter-annotator agreement (IAA). Using the obtained data, we compile multi- and single-labeled dataset variants using different label aggregation schemes. Finally, we evaluate three different baseline WSD models on both dataset variants and report on the insights gained. We make both dataset variants freely available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alagic-snajder-2016-cro36wsd">
<titleInfo>
<title>Cro36WSD: A Lexical Sample for Croatian Word Sense Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Domagoj</namePart>
<namePart type="family">Alagić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce Cro36WSD, a freely-available medium-sized lexical sample for Croatian word sense disambiguation (WSD).Cro36WSD comprises 36 words: 12 adjectives, 12 nouns, and 12 verbs, balanced across both frequency bands and polysemy levels. We adopt the multi-label annotation scheme in the hope of lessening the drawbacks of discrete sense inventories and obtaining more realistic annotations from human experts. Sense-annotated data is collected through multiple annotation rounds to ensure high-quality annotations: with a 115 person-hours effort we reached an inter-annotator agreement score of 0.877. We analyze the obtained data and perform a correlation analysis between several relevant variables, including word frequency, number of senses, sense distribution skewness, average annotation time, and the observed inter-annotator agreement (IAA). Using the obtained data, we compile multi- and single-labeled dataset variants using different label aggregation schemes. Finally, we evaluate three different baseline WSD models on both dataset variants and report on the insights gained. We make both dataset variants freely available.</abstract>
<identifier type="citekey">alagic-snajder-2016-cro36wsd</identifier>
<location>
<url>https://aclanthology.org/L16-1267</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1689</start>
<end>1694</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cro36WSD: A Lexical Sample for Croatian Word Sense Disambiguation
%A Alagić, Domagoj
%A Šnajder, Jan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F alagic-snajder-2016-cro36wsd
%X We introduce Cro36WSD, a freely-available medium-sized lexical sample for Croatian word sense disambiguation (WSD).Cro36WSD comprises 36 words: 12 adjectives, 12 nouns, and 12 verbs, balanced across both frequency bands and polysemy levels. We adopt the multi-label annotation scheme in the hope of lessening the drawbacks of discrete sense inventories and obtaining more realistic annotations from human experts. Sense-annotated data is collected through multiple annotation rounds to ensure high-quality annotations: with a 115 person-hours effort we reached an inter-annotator agreement score of 0.877. We analyze the obtained data and perform a correlation analysis between several relevant variables, including word frequency, number of senses, sense distribution skewness, average annotation time, and the observed inter-annotator agreement (IAA). Using the obtained data, we compile multi- and single-labeled dataset variants using different label aggregation schemes. Finally, we evaluate three different baseline WSD models on both dataset variants and report on the insights gained. We make both dataset variants freely available.
%U https://aclanthology.org/L16-1267
%P 1689-1694
Markdown (Informal)
[Cro36WSD: A Lexical Sample for Croatian Word Sense Disambiguation](https://aclanthology.org/L16-1267) (Alagić & Šnajder, LREC 2016)
ACL