@inproceedings{vintar-etal-2020-mining,
title = "Mining Semantic Relations from Comparable Corpora through Intersections of Word Embeddings",
author = "Vintar, {\v{S}}pela and
Gr{\v{c}}i{\'c} Simeunovi{\'c}, Larisa and
Martinc, Matej and
Pollak, Senja and
Stepi{\v{s}}nik, Uro{\v{s}}",
editor = "Rapp, Reinhard and
Zweigenbaum, Pierre and
Sharoff, Serge",
booktitle = "Proceedings of the 13th Workshop on Building and Using Comparable Corpora",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.bucc-1.5",
pages = "29--34",
abstract = "We report an experiment aimed at extracting words expressing a specific semantic relation using intersections of word embeddings. In a multilingual frame-based domain model, specific features of a concept are typically described through a set of non-arbitrary semantic relations. In karstology, our domain of choice which we are exploring though a comparable corpus in English and Croatian, karst phenomena such as landforms are usually described through their FORM, LOCATION, CAUSE, FUNCTION and COMPOSITION. We propose an approach to mine words pertaining to each of these relations by using a small number of seed adjectives, for which we retrieve closest words using word embeddings and then use intersections of these neighbourhoods to refine our search. Such cross-language expansion of semantically-rich vocabulary is a valuable aid in improving the coverage of a multilingual knowledge base, but also in exploring differences between languages in their respective conceptualisations of the domain.",
language = "English",
ISBN = "979-10-95546-42-9",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vintar-etal-2020-mining">
<titleInfo>
<title>Mining Semantic Relations from Comparable Corpora through Intersections of Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Špela</namePart>
<namePart type="family">Vintar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larisa</namePart>
<namePart type="family">Grčić Simeunović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matej</namePart>
<namePart type="family">Martinc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uroš</namePart>
<namePart type="family">Stepišnik</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 13th Workshop on Building and Using Comparable Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reinhard</namePart>
<namePart type="family">Rapp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</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">979-10-95546-42-9</identifier>
</relatedItem>
<abstract>We report an experiment aimed at extracting words expressing a specific semantic relation using intersections of word embeddings. In a multilingual frame-based domain model, specific features of a concept are typically described through a set of non-arbitrary semantic relations. In karstology, our domain of choice which we are exploring though a comparable corpus in English and Croatian, karst phenomena such as landforms are usually described through their FORM, LOCATION, CAUSE, FUNCTION and COMPOSITION. We propose an approach to mine words pertaining to each of these relations by using a small number of seed adjectives, for which we retrieve closest words using word embeddings and then use intersections of these neighbourhoods to refine our search. Such cross-language expansion of semantically-rich vocabulary is a valuable aid in improving the coverage of a multilingual knowledge base, but also in exploring differences between languages in their respective conceptualisations of the domain.</abstract>
<identifier type="citekey">vintar-etal-2020-mining</identifier>
<location>
<url>https://aclanthology.org/2020.bucc-1.5</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>29</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mining Semantic Relations from Comparable Corpora through Intersections of Word Embeddings
%A Vintar, Špela
%A Grčić Simeunović, Larisa
%A Martinc, Matej
%A Pollak, Senja
%A Stepišnik, Uroš
%Y Rapp, Reinhard
%Y Zweigenbaum, Pierre
%Y Sharoff, Serge
%S Proceedings of the 13th Workshop on Building and Using Comparable Corpora
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-42-9
%G English
%F vintar-etal-2020-mining
%X We report an experiment aimed at extracting words expressing a specific semantic relation using intersections of word embeddings. In a multilingual frame-based domain model, specific features of a concept are typically described through a set of non-arbitrary semantic relations. In karstology, our domain of choice which we are exploring though a comparable corpus in English and Croatian, karst phenomena such as landforms are usually described through their FORM, LOCATION, CAUSE, FUNCTION and COMPOSITION. We propose an approach to mine words pertaining to each of these relations by using a small number of seed adjectives, for which we retrieve closest words using word embeddings and then use intersections of these neighbourhoods to refine our search. Such cross-language expansion of semantically-rich vocabulary is a valuable aid in improving the coverage of a multilingual knowledge base, but also in exploring differences between languages in their respective conceptualisations of the domain.
%U https://aclanthology.org/2020.bucc-1.5
%P 29-34
Markdown (Informal)
[Mining Semantic Relations from Comparable Corpora through Intersections of Word Embeddings](https://aclanthology.org/2020.bucc-1.5) (Vintar et al., BUCC 2020)
ACL