@inproceedings{nandakumar-etal-2019-well,
title = "How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions",
author = "Nandakumar, Navnita and
Baldwin, Timothy and
Salehi, Bahar",
editor = "Rogers, Anna and
Drozd, Aleksandr and
Rumshisky, Anna and
Goldberg, Yoav",
booktitle = "Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for {NLP}",
month = jun,
year = "2019",
address = "Minneapolis, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-2004",
doi = "10.18653/v1/W19-2004",
pages = "27--34",
abstract = "In this paper, we apply various embedding methods on multiword expressions to study how well they capture the nuances of non-compositional data. Our results from a pool of word-, character-, and document-level embbedings suggest that Word2vec performs the best, followed by FastText and Infersent. Moreover, we find that recently-proposed contextualised embedding models such as Bert and ELMo are not adept at handling non-compositionality in multiword expressions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nandakumar-etal-2019-well">
<titleInfo>
<title>How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Navnita</namePart>
<namePart type="family">Nandakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bahar</namePart>
<namePart type="family">Salehi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Drozd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we apply various embedding methods on multiword expressions to study how well they capture the nuances of non-compositional data. Our results from a pool of word-, character-, and document-level embbedings suggest that Word2vec performs the best, followed by FastText and Infersent. Moreover, we find that recently-proposed contextualised embedding models such as Bert and ELMo are not adept at handling non-compositionality in multiword expressions.</abstract>
<identifier type="citekey">nandakumar-etal-2019-well</identifier>
<identifier type="doi">10.18653/v1/W19-2004</identifier>
<location>
<url>https://aclanthology.org/W19-2004</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>27</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions
%A Nandakumar, Navnita
%A Baldwin, Timothy
%A Salehi, Bahar
%Y Rogers, Anna
%Y Drozd, Aleksandr
%Y Rumshisky, Anna
%Y Goldberg, Yoav
%S Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, USA
%F nandakumar-etal-2019-well
%X In this paper, we apply various embedding methods on multiword expressions to study how well they capture the nuances of non-compositional data. Our results from a pool of word-, character-, and document-level embbedings suggest that Word2vec performs the best, followed by FastText and Infersent. Moreover, we find that recently-proposed contextualised embedding models such as Bert and ELMo are not adept at handling non-compositionality in multiword expressions.
%R 10.18653/v1/W19-2004
%U https://aclanthology.org/W19-2004
%U https://doi.org/10.18653/v1/W19-2004
%P 27-34
Markdown (Informal)
[How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions](https://aclanthology.org/W19-2004) (Nandakumar et al., RepEval 2019)
ACL