Please use this identifier to cite or link to this item:

Title: Word Embedding Evaluation in Downstream Tasks and Semantic Analogies
Authors: Santos, Joaquim
Consoli, Bernardo
Vieira, Renata
Keywords: Language models
Issue Date: May-2020
Publisher: LREC/ELRA
Citation: SANTOS, Joaquim; CONSOLI, Bernardo; VIEIRA, Renata. Word Embedding Evaluation in Downstream Tasks and Semantic Analogies. In: Proceedings of The 12th Language Resources and Evaluation Conference. 2020. p. 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 language, 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 passing the text in parts to the WE generating algorithm may cause loss of quality.
Type: article
Appears in Collections:CIDEHUS - Artigos em Livros de Actas/Proceedings

Files in This Item:

File Description SizeFormat
2020.lrec-1.594.pdf236.13 kBAdobe PDFView/Open
FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpaceOrkut
Formato BibTex mendeley Endnote Logotipo do DeGóis 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Dspace Dspace
DSpace Software, version 1.6.2 Copyright © 2002-2008 MIT and Hewlett-Packard - Feedback
UEvora B-On Curriculum DeGois