@inproceedings{santos-etal-2020-word,
title = "Word Embedding Evaluation in Downstream Tasks and Semantic Analogies",
author = "Santos, Joaquim and
Consoli, Bernardo and
Vieira, Renata",
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-1.594",
pages = "4828--4834",
abstract = "Language Models have long been a prolific area of study in the field of Natural Language Processing (NLP). One of the newer kinds of language models, and some of the most used, are Word Embeddings (WE). WE are vector space representations of a vocabulary learned by a non-supervised neural network based on the context in which words appear. WE have been widely used in downstream tasks in many areas of study in NLP. These areas usually use these vector models as a feature in the processing of textual data. This paper presents the evaluation of newly released WE models for the Portuguese langauage, trained with a corpus composed of 4.9 billion tokens. The first evaluation presented an intrinsic task in which WEs had to correctly build semantic and syntactic relations. The second evaluation presented an extrinsic task in which the WE models were used in two downstream tasks: Named Entity Recognition and Semantic Similarity between Sentences. Our results show that a diverse and comprehensive corpus can often outperform a larger, less textually diverse corpus, and that batch training may cause quality loss in WE models.",
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="santos-etal-2020-word">
<titleInfo>
<title>Word Embedding Evaluation in Downstream Tasks and Semantic Analogies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joaquim</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernardo</namePart>
<namePart type="family">Consoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renata</namePart>
<namePart type="family">Vieira</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>Language Models have long been a prolific area of study in the field of Natural Language Processing (NLP). One of the newer kinds of language models, and some of the most used, are Word Embeddings (WE). WE are vector space representations of a vocabulary learned by a non-supervised neural network based on the context in which words appear. WE have been widely used in downstream tasks in many areas of study in NLP. These areas usually use these vector models as a feature in the processing of textual data. This paper presents the evaluation of newly released WE models for the Portuguese langauage, trained with a corpus composed of 4.9 billion tokens. The first evaluation presented an intrinsic task in which WEs had to correctly build semantic and syntactic relations. The second evaluation presented an extrinsic task in which the WE models were used in two downstream tasks: Named Entity Recognition and Semantic Similarity between Sentences. Our results show that a diverse and comprehensive corpus can often outperform a larger, less textually diverse corpus, and that batch training may cause quality loss in WE models.</abstract>
<identifier type="citekey">santos-etal-2020-word</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.594</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4828</start>
<end>4834</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Embedding Evaluation in Downstream Tasks and Semantic Analogies
%A Santos, Joaquim
%A Consoli, Bernardo
%A Vieira, Renata
%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 santos-etal-2020-word
%X Language Models have long been a prolific area of study in the field of Natural Language Processing (NLP). One of the newer kinds of language models, and some of the most used, are Word Embeddings (WE). WE are vector space representations of a vocabulary learned by a non-supervised neural network based on the context in which words appear. WE have been widely used in downstream tasks in many areas of study in NLP. These areas usually use these vector models as a feature in the processing of textual data. This paper presents the evaluation of newly released WE models for the Portuguese langauage, trained with a corpus composed of 4.9 billion tokens. The first evaluation presented an intrinsic task in which WEs had to correctly build semantic and syntactic relations. The second evaluation presented an extrinsic task in which the WE models were used in two downstream tasks: Named Entity Recognition and Semantic Similarity between Sentences. Our results show that a diverse and comprehensive corpus can often outperform a larger, less textually diverse corpus, and that batch training may cause quality loss in WE models.
%U https://aclanthology.org/2020.lrec-1.594
%P 4828-4834
Markdown (Informal)
[Word Embedding Evaluation in Downstream Tasks and Semantic Analogies](https://aclanthology.org/2020.lrec-1.594) (Santos et al., LREC 2020)
ACL