@inproceedings{rudnicka-naskret-2020-dataset,
title = "A Dataset of Translational Equivalents Built on the Basis of pl{W}ord{N}et-{P}rinceton {W}ord{N}et Synset Mapping",
author = "Rudnicka, Ewa and
Naskr{\k{e}}t, Tomasz",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.398",
pages = "3260--3264",
abstract = "The paper presents a dataset of 11,000 Polish-English translational equivalents in the form of pairs of plWordNet and Princeton WordNet lexical units linked by three types of equivalence links: strong equivalence, regular equivalence, and weak equivalence. The resource consists of the two subsets. The first subset was built in result of manual annotation of an extended sample of Polish-English sense pairs partly randomly extracted from synsets linked by interlingual relations such as I-synononymy, I-partial synonymy and I-hyponymy and partly manually selected from the surrounding synsets in the hypernymy hierarchy. The second subset was created as a result of the manual checkup of an automatically generated lists of pairs of sense equivalents on the basis of a couple of simple, rule-based heuristics. For both subsets, the same methodology of equivalence annotation was adopted based on the verification of a set of formal, semantic-pragmatic and translational features. The constructed dataset is a novum in the wordnet domain and can facilitate the precision of bilingual NLP tasks such as automatic translation, bilingual word sense disambiguation and sentiment annotation.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rudnicka-naskret-2020-dataset">
<titleInfo>
<title>A Dataset of Translational Equivalents Built on the Basis of plWordNet-Princeton WordNet Synset Mapping</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ewa</namePart>
<namePart type="family">Rudnicka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Naskręt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>The paper presents a dataset of 11,000 Polish-English translational equivalents in the form of pairs of plWordNet and Princeton WordNet lexical units linked by three types of equivalence links: strong equivalence, regular equivalence, and weak equivalence. The resource consists of the two subsets. The first subset was built in result of manual annotation of an extended sample of Polish-English sense pairs partly randomly extracted from synsets linked by interlingual relations such as I-synononymy, I-partial synonymy and I-hyponymy and partly manually selected from the surrounding synsets in the hypernymy hierarchy. The second subset was created as a result of the manual checkup of an automatically generated lists of pairs of sense equivalents on the basis of a couple of simple, rule-based heuristics. For both subsets, the same methodology of equivalence annotation was adopted based on the verification of a set of formal, semantic-pragmatic and translational features. The constructed dataset is a novum in the wordnet domain and can facilitate the precision of bilingual NLP tasks such as automatic translation, bilingual word sense disambiguation and sentiment annotation.</abstract>
<identifier type="citekey">rudnicka-naskret-2020-dataset</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.398</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3260</start>
<end>3264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dataset of Translational Equivalents Built on the Basis of plWordNet-Princeton WordNet Synset Mapping
%A Rudnicka, Ewa
%A Naskręt, Tomasz
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F rudnicka-naskret-2020-dataset
%X The paper presents a dataset of 11,000 Polish-English translational equivalents in the form of pairs of plWordNet and Princeton WordNet lexical units linked by three types of equivalence links: strong equivalence, regular equivalence, and weak equivalence. The resource consists of the two subsets. The first subset was built in result of manual annotation of an extended sample of Polish-English sense pairs partly randomly extracted from synsets linked by interlingual relations such as I-synononymy, I-partial synonymy and I-hyponymy and partly manually selected from the surrounding synsets in the hypernymy hierarchy. The second subset was created as a result of the manual checkup of an automatically generated lists of pairs of sense equivalents on the basis of a couple of simple, rule-based heuristics. For both subsets, the same methodology of equivalence annotation was adopted based on the verification of a set of formal, semantic-pragmatic and translational features. The constructed dataset is a novum in the wordnet domain and can facilitate the precision of bilingual NLP tasks such as automatic translation, bilingual word sense disambiguation and sentiment annotation.
%U https://aclanthology.org/2020.lrec-1.398
%P 3260-3264
Markdown (Informal)
[A Dataset of Translational Equivalents Built on the Basis of plWordNet-Princeton WordNet Synset Mapping](https://aclanthology.org/2020.lrec-1.398) (Rudnicka & Naskręt, LREC 2020)
ACL