@article{utt-pado-2014-crosslingual,
title = "Crosslingual and Multilingual Construction of Syntax-Based Vector Space Models",
author = "Utt, Jason and
Pad{\'o}, Sebastian",
journal = "Transactions of the Association for Computational Linguistics",
volume = "2",
year = "2014",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q14-1020",
doi = "10.1162/tacl_a_00180",
pages = "245--258",
abstract = "Syntax-based distributional models of lexical semantics provide a flexible and linguistically adequate representation of co-occurrence information. However, their construction requires large, accurately parsed corpora, which are unavailable for most languages. In this paper, we develop a number of methods to overcome this obstacle. We describe (a) a crosslingual approach that constructs a syntax-based model for a new language requiring only an English resource and a translation lexicon; and (b) multilingual approaches that combine crosslingual with monolingual information, subject to availability. We evaluate on two lexical semantic benchmarks in German and Croatian. We find that the models exhibit complementary profiles: crosslingual models yield higher accuracies while monolingual models provide better coverage. In addition, we show that simple multilingual models can successfully combine their strengths.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="utt-pado-2014-crosslingual">
<titleInfo>
<title>Crosslingual and Multilingual Construction of Syntax-Based Vector Space Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Utt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Padó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre>journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre>academic journal</genre>
</relatedItem>
<abstract>Syntax-based distributional models of lexical semantics provide a flexible and linguistically adequate representation of co-occurrence information. However, their construction requires large, accurately parsed corpora, which are unavailable for most languages. In this paper, we develop a number of methods to overcome this obstacle. We describe (a) a crosslingual approach that constructs a syntax-based model for a new language requiring only an English resource and a translation lexicon; and (b) multilingual approaches that combine crosslingual with monolingual information, subject to availability. We evaluate on two lexical semantic benchmarks in German and Croatian. We find that the models exhibit complementary profiles: crosslingual models yield higher accuracies while monolingual models provide better coverage. In addition, we show that simple multilingual models can successfully combine their strengths.</abstract>
<identifier type="citekey">utt-pado-2014-crosslingual</identifier>
<identifier type="doi">10.1162/tacl_a_00180</identifier>
<location>
<url>https://aclanthology.org/Q14-1020</url>
</location>
<part>
<date>2014</date>
<detail type="volume"><number>2</number></detail>
<extent unit="page">
<start>245</start>
<end>258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Crosslingual and Multilingual Construction of Syntax-Based Vector Space Models
%A Utt, Jason
%A Padó, Sebastian
%J Transactions of the Association for Computational Linguistics
%D 2014
%V 2
%I MIT Press
%C Cambridge, MA
%F utt-pado-2014-crosslingual
%X Syntax-based distributional models of lexical semantics provide a flexible and linguistically adequate representation of co-occurrence information. However, their construction requires large, accurately parsed corpora, which are unavailable for most languages. In this paper, we develop a number of methods to overcome this obstacle. We describe (a) a crosslingual approach that constructs a syntax-based model for a new language requiring only an English resource and a translation lexicon; and (b) multilingual approaches that combine crosslingual with monolingual information, subject to availability. We evaluate on two lexical semantic benchmarks in German and Croatian. We find that the models exhibit complementary profiles: crosslingual models yield higher accuracies while monolingual models provide better coverage. In addition, we show that simple multilingual models can successfully combine their strengths.
%9 journal article
%R 10.1162/tacl_a_00180
%U https://aclanthology.org/Q14-1020
%U https://doi.org/10.1162/tacl_a_00180
%P 245-258
Markdown (Informal)
[Crosslingual and Multilingual Construction of Syntax-Based Vector Space Models](https://aclanthology.org/Q14-1020) (Utt & Padó, TACL 2014)
ACL