2026-07-25T22:06:55Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:16763 2024-03-12T12:00:52Z ddc:004 open_access

Reasoning with Portuguese Word Embeddings Cunha, Luís Filipe Almeida, J. João Simões, Alberto Word Embeddings Word2Vec Evaluation Methods Representing words with semantic distributions to create ML models is a widely used technique to perform Natural Language processing tasks. In this paper, we trained word embedding models with different types of Portuguese corpora, analyzing the influence of the models' parameterization, the corpora size, and domain. Then we validated each model with the classical evaluation methods available: four words analogies and measurement of the similarity of pairs of words. In addition to these methods, we proposed new alternative techniques to validate word embedding models, presenting new resources for this purpose. Finally, we discussed the obtained results and argued about some limitations of the word embedding models' evaluation methods. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Luís Filipe Cunha and J. João Almeida and Alberto Simões 2022 Is Part Of OASIcs, Volume 104, 11th Symposium on Languages, Applications and Technologies (SLATE 2022) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.SLATE.2022.17 urn:nbn:de:0030-drops-167636 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.SLATE.2022.17 eng https://creativecommons.org/licenses/by/4.0/legalcode