Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSA

In recent years, latent semantic analysis (LSA) has reached a level of maturity at which its presence is ubiquitous in technology as well as in simulation of cognitive processes. In spite of this, in recent years there has been a trend of subjecting LSA to some criticisms, usually because it is comp...

ver descrição completa

Detalhes bibliográficos
Autores: Jorge Botana, Guillermo de, Olmos, Ricardo, Luzón Encabo, José María
Tipo de documento: artigo
Data de publicação:2020
País:España
Recursos:Universidad Complutense de Madrid (UCM)
Repositório:Docta Complutense
Idioma:inglês
OAI Identifier:oai:docta.ucm.es:20.500.14352/127360
Acesso em linha:https://hdl.handle.net/20.500.14352/127360
Access Level:Acceso aberto
Palavra-chave:Latent Semantic Analysis
LSA
Word2vec
Spatial Models
Distributional Models
Topic Model
Psicología (Psicología)
61 Psicología
id ES_2442e3cd90f2f8f35dcde814d5663d5c
oai_identifier_str oai:docta.ucm.es:20.500.14352/127360
network_acronym_str ES
network_name_str España
repository_id_str
spelling Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSAJorge Botana, Guillermo deOlmos, RicardoLuzón Encabo, José MaríaLatent Semantic AnalysisLSAWord2vecSpatial ModelsDistributional ModelsTopic ModelPsicología (Psicología)61 PsicologíaIn recent years, latent semantic analysis (LSA) has reached a level of maturity at which its presence is ubiquitous in technology as well as in simulation of cognitive processes. In spite of this, in recent years there has been a trend of subjecting LSA to some criticisms, usually because it is compared to other models in very specific tasks and conditions and sometimes without having good knowledge of what the semantic representation of LSA means, and without exploiting all the possibilities of which LSA is capable other than the cosine. This paper provides a critical review to clarify some of the misunderstandings regarding LSA and other space models. The historical stability of the predecessors of LSA, the representational structure of word meaning and the multiple topologies that could arise from a semantic space, the computation of similarity, the myth that LSA dimensions have no meaning, the computational and algorithm plausibility to account for meaning acquisition in LSA (in contrast to others models based on online mechanisms), the possibilities of spatial models to substantiate recent proposals, and, in general, the characteristics of classic vector models and their ease and flexibility to simulate some cognitive phenomena will be reviewed. The review highlights the similarity between LSA and other techniques and proposes using long LSA experiences in other models, especially in predicting models such as word2vec. In sum, it emphasizes the lessons that can be learned from comparing LSA-based models to other models, rather than making statements about “the best.”SpringerUniversidad Complutense de Madrid20202020-07-0120202020-07-01journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/20.500.14352/127360reponame:Docta Complutenseinstname:Universidad Complutense de Madrid (UCM)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:docta.ucm.es:20.500.14352/1273602026-06-02T12:44:21Z
dc.title.none.fl_str_mv Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSA
title Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSA
spellingShingle Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSA
Jorge Botana, Guillermo de
Latent Semantic Analysis
LSA
Word2vec
Spatial Models
Distributional Models
Topic Model
Psicología (Psicología)
61 Psicología
title_short Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSA
title_full Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSA
title_fullStr Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSA
title_full_unstemmed Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSA
title_sort Bridging the theoretical gap between semantic representation models without the pressure of a ranking: Some lessons learnt from LSA
dc.creator.none.fl_str_mv Jorge Botana, Guillermo de
Olmos, Ricardo
Luzón Encabo, José María
author Jorge Botana, Guillermo de
author_facet Jorge Botana, Guillermo de
Olmos, Ricardo
Luzón Encabo, José María
author_role author
author2 Olmos, Ricardo
Luzón Encabo, José María
author2_role author
author
dc.contributor.none.fl_str_mv Universidad Complutense de Madrid
dc.subject.none.fl_str_mv Latent Semantic Analysis
LSA
Word2vec
Spatial Models
Distributional Models
Topic Model
Psicología (Psicología)
61 Psicología
topic Latent Semantic Analysis
LSA
Word2vec
Spatial Models
Distributional Models
Topic Model
Psicología (Psicología)
61 Psicología
description In recent years, latent semantic analysis (LSA) has reached a level of maturity at which its presence is ubiquitous in technology as well as in simulation of cognitive processes. In spite of this, in recent years there has been a trend of subjecting LSA to some criticisms, usually because it is compared to other models in very specific tasks and conditions and sometimes without having good knowledge of what the semantic representation of LSA means, and without exploiting all the possibilities of which LSA is capable other than the cosine. This paper provides a critical review to clarify some of the misunderstandings regarding LSA and other space models. The historical stability of the predecessors of LSA, the representational structure of word meaning and the multiple topologies that could arise from a semantic space, the computation of similarity, the myth that LSA dimensions have no meaning, the computational and algorithm plausibility to account for meaning acquisition in LSA (in contrast to others models based on online mechanisms), the possibilities of spatial models to substantiate recent proposals, and, in general, the characteristics of classic vector models and their ease and flexibility to simulate some cognitive phenomena will be reviewed. The review highlights the similarity between LSA and other techniques and proposes using long LSA experiences in other models, especially in predicting models such as word2vec. In sum, it emphasizes the lessons that can be learned from comparing LSA-based models to other models, rather than making statements about “the best.”
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-07-01
2020
2020-07-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14352/127360
url https://hdl.handle.net/20.500.14352/127360
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:Docta Complutense
instname:Universidad Complutense de Madrid (UCM)
instname_str Universidad Complutense de Madrid (UCM)
reponame_str Docta Complutense
collection Docta Complutense
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869404689224695808
score 15,81155

Registros relacionados