@inproceedings{majewska-etal-2020-spatial,
title = "Spatial Multi-Arrangement for Clustering and Multi-way Similarity Dataset Construction",
author = "Majewska, Olga and
McCarthy, Diana and
van den Bosch, Jasper and
Kriegeskorte, Nikolaus and
Vuli{\'c}, Ivan and
Korhonen, Anna",
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-1.705",
pages = "5749--5758",
abstract = "We present a novel methodology for fast bottom-up creation of large-scale semantic similarity resources to support development and evaluation of NLP systems. Our work targets verb similarity, but the methodology is equally applicable to other parts of speech. Our approach circumvents the bottleneck of slow and expensive manual development of lexical resources by leveraging semantic intuitions of native speakers and adapting a spatial multi-arrangement approach from cognitive neuroscience, used before only with visual stimuli, to lexical stimuli. Our approach critically obtains judgments of word similarity in the context of a set of related words, rather than of word pairs in isolation. We also handle lexical ambiguity as a natural consequence of a two-phase process where verbs are placed in broad semantic classes prior to the fine-grained spatial similarity judgments. Our proposed design produces a large-scale verb resource comprising 17 relatedness-based classes and a verb similarity dataset containing similarity scores for 29,721 unique verb pairs and 825 target verbs, which we release with this paper.",
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="majewska-etal-2020-spatial">
<titleInfo>
<title>Spatial Multi-Arrangement for Clustering and Multi-way Similarity Dataset Construction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Majewska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">McCarthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jasper</namePart>
<namePart type="family">van den Bosch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaus</namePart>
<namePart type="family">Kriegeskorte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</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>We present a novel methodology for fast bottom-up creation of large-scale semantic similarity resources to support development and evaluation of NLP systems. Our work targets verb similarity, but the methodology is equally applicable to other parts of speech. Our approach circumvents the bottleneck of slow and expensive manual development of lexical resources by leveraging semantic intuitions of native speakers and adapting a spatial multi-arrangement approach from cognitive neuroscience, used before only with visual stimuli, to lexical stimuli. Our approach critically obtains judgments of word similarity in the context of a set of related words, rather than of word pairs in isolation. We also handle lexical ambiguity as a natural consequence of a two-phase process where verbs are placed in broad semantic classes prior to the fine-grained spatial similarity judgments. Our proposed design produces a large-scale verb resource comprising 17 relatedness-based classes and a verb similarity dataset containing similarity scores for 29,721 unique verb pairs and 825 target verbs, which we release with this paper.</abstract>
<identifier type="citekey">majewska-etal-2020-spatial</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.705</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5749</start>
<end>5758</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spatial Multi-Arrangement for Clustering and Multi-way Similarity Dataset Construction
%A Majewska, Olga
%A McCarthy, Diana
%A van den Bosch, Jasper
%A Kriegeskorte, Nikolaus
%A Vulić, Ivan
%A Korhonen, Anna
%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 majewska-etal-2020-spatial
%X We present a novel methodology for fast bottom-up creation of large-scale semantic similarity resources to support development and evaluation of NLP systems. Our work targets verb similarity, but the methodology is equally applicable to other parts of speech. Our approach circumvents the bottleneck of slow and expensive manual development of lexical resources by leveraging semantic intuitions of native speakers and adapting a spatial multi-arrangement approach from cognitive neuroscience, used before only with visual stimuli, to lexical stimuli. Our approach critically obtains judgments of word similarity in the context of a set of related words, rather than of word pairs in isolation. We also handle lexical ambiguity as a natural consequence of a two-phase process where verbs are placed in broad semantic classes prior to the fine-grained spatial similarity judgments. Our proposed design produces a large-scale verb resource comprising 17 relatedness-based classes and a verb similarity dataset containing similarity scores for 29,721 unique verb pairs and 825 target verbs, which we release with this paper.
%U https://aclanthology.org/2020.lrec-1.705
%P 5749-5758
Markdown (Informal)
[Spatial Multi-Arrangement for Clustering and Multi-way Similarity Dataset Construction](https://aclanthology.org/2020.lrec-1.705) (Majewska et al., LREC 2020)
ACL