@inproceedings{torregrossa-etal-2020-correlation,
title = "On the Correlation of Word Embedding Evaluation Metrics",
author = "Torregrossa, Fran{\c{c}}ois and
Claveau, Vincent and
Kooli, Nihel and
Gravier, Guillaume and
Allesiardo, Robin",
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-1.589",
pages = "4789--4797",
abstract = "Word embeddings intervene in a wide range of natural language processing tasks. These geometrical representations are easy to manipulate for automatic systems. Therefore, they quickly invaded all areas of language processing. While they surpass all predecessors, it is still not straightforward why and how they do so. In this article, we propose to investigate all kind of evaluation metrics on various datasets in order to discover how they correlate with each other. Those correlations lead to 1) a fast solution to select the best word embeddings among many others, 2) a new criterion that may improve the current state of static Euclidean word embeddings, and 3) a way to create a set of complementary datasets, i.e. each dataset quantifies a different aspect of word embeddings.",
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="torregrossa-etal-2020-correlation">
<titleInfo>
<title>On the Correlation of Word Embedding Evaluation Metrics</title>
</titleInfo>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Torregrossa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Claveau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nihel</namePart>
<namePart type="family">Kooli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Gravier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Allesiardo</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>Word embeddings intervene in a wide range of natural language processing tasks. These geometrical representations are easy to manipulate for automatic systems. Therefore, they quickly invaded all areas of language processing. While they surpass all predecessors, it is still not straightforward why and how they do so. In this article, we propose to investigate all kind of evaluation metrics on various datasets in order to discover how they correlate with each other. Those correlations lead to 1) a fast solution to select the best word embeddings among many others, 2) a new criterion that may improve the current state of static Euclidean word embeddings, and 3) a way to create a set of complementary datasets, i.e. each dataset quantifies a different aspect of word embeddings.</abstract>
<identifier type="citekey">torregrossa-etal-2020-correlation</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.589</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4789</start>
<end>4797</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Correlation of Word Embedding Evaluation Metrics
%A Torregrossa, François
%A Claveau, Vincent
%A Kooli, Nihel
%A Gravier, Guillaume
%A Allesiardo, Robin
%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 torregrossa-etal-2020-correlation
%X Word embeddings intervene in a wide range of natural language processing tasks. These geometrical representations are easy to manipulate for automatic systems. Therefore, they quickly invaded all areas of language processing. While they surpass all predecessors, it is still not straightforward why and how they do so. In this article, we propose to investigate all kind of evaluation metrics on various datasets in order to discover how they correlate with each other. Those correlations lead to 1) a fast solution to select the best word embeddings among many others, 2) a new criterion that may improve the current state of static Euclidean word embeddings, and 3) a way to create a set of complementary datasets, i.e. each dataset quantifies a different aspect of word embeddings.
%U https://aclanthology.org/2020.lrec-1.589
%P 4789-4797
Markdown (Informal)
[On the Correlation of Word Embedding Evaluation Metrics](https://aclanthology.org/2020.lrec-1.589) (Torregrossa et al., LREC 2020)
ACL
- François Torregrossa, Vincent Claveau, Nihel Kooli, Guillaume Gravier, and Robin Allesiardo. 2020. On the Correlation of Word Embedding Evaluation Metrics. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4789–4797, Marseille, France. European Language Resources Association.