@article{mrksic-etal-2017-semantic,
title = "Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints",
author = "Mrk{\v{s}}i{\'c}, Nikola and
Vuli{\'c}, Ivan and
{\'O} S{\'e}aghdha, Diarmuid and
Leviant, Ira and
Reichart, Roi and
Ga{\v{s}}i{\'c}, Milica and
Korhonen, Anna and
Young, Steve",
editor = "Lee, Lillian and
Johnson, Mark and
Toutanova, Kristina",
journal = "Transactions of the Association for Computational Linguistics",
volume = "5",
year = "2017",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q17-1022",
doi = "10.1162/tacl_a_00063",
pages = "309--324",
abstract = "We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-lingual resources, yielding semantically specialized cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct high-quality vector spaces for a plethora of different languages, facilitating semantic transfer from high- to lower-resource ones. The effectiveness of our approach is demonstrated with state-of-the-art results on semantic similarity datasets in six languages. We next show that Attract-Repel-specialized vectors boost performance in the downstream task of dialogue state tracking (DST) across multiple languages. Finally, we show that cross-lingual vector spaces produced by our algorithm facilitate the training of multilingual DST models, which brings further performance improvements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mrksic-etal-2017-semantic">
<titleInfo>
<title>Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Mrkšić</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">Diarmuid</namePart>
<namePart type="family">Ó Séaghdha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ira</namePart>
<namePart type="family">Leviant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Gašić</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>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Young</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">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 authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-lingual resources, yielding semantically specialized cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct high-quality vector spaces for a plethora of different languages, facilitating semantic transfer from high- to lower-resource ones. The effectiveness of our approach is demonstrated with state-of-the-art results on semantic similarity datasets in six languages. We next show that Attract-Repel-specialized vectors boost performance in the downstream task of dialogue state tracking (DST) across multiple languages. Finally, we show that cross-lingual vector spaces produced by our algorithm facilitate the training of multilingual DST models, which brings further performance improvements.</abstract>
<identifier type="citekey">mrksic-etal-2017-semantic</identifier>
<identifier type="doi">10.1162/tacl_a_00063</identifier>
<location>
<url>https://aclanthology.org/Q17-1022</url>
</location>
<part>
<date>2017</date>
<detail type="volume"><number>5</number></detail>
<extent unit="page">
<start>309</start>
<end>324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
%A Mrkšić, Nikola
%A Vulić, Ivan
%A Ó Séaghdha, Diarmuid
%A Leviant, Ira
%A Reichart, Roi
%A Gašić, Milica
%A Korhonen, Anna
%A Young, Steve
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F mrksic-etal-2017-semantic
%X We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-lingual resources, yielding semantically specialized cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct high-quality vector spaces for a plethora of different languages, facilitating semantic transfer from high- to lower-resource ones. The effectiveness of our approach is demonstrated with state-of-the-art results on semantic similarity datasets in six languages. We next show that Attract-Repel-specialized vectors boost performance in the downstream task of dialogue state tracking (DST) across multiple languages. Finally, we show that cross-lingual vector spaces produced by our algorithm facilitate the training of multilingual DST models, which brings further performance improvements.
%R 10.1162/tacl_a_00063
%U https://aclanthology.org/Q17-1022
%U https://doi.org/10.1162/tacl_a_00063
%P 309-324
Markdown (Informal)
[Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints](https://aclanthology.org/Q17-1022) (Mrkšić et al., TACL 2017)
ACL