mlsanityData to 7 Oct 2026

Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks

arXiv 1708.06025 ↗First posted 20 Aug 2017cs.CLcited by 13

Not on the map. Why?

Abstract (arXiv)

Word embeddings have been found to provide meaningful representations for words in an efficient way; therefore, they have become common in Natural Language Processing sys- tems. In this paper, we evaluated different word embedding models trained on a large Portuguese corpus, including both Brazilian and European variants. We trained 31 word embedding models using FastText, GloVe, Wang2Vec and Word2Vec. We evaluated them intrinsically on syntactic and semantic analogies and extrinsically on POS tagging and sentence semantic similarity tasks. The obtained results suggest that word analogies are not appropriate for word embedding evaluation; task-specific evaluations appear to be a better option.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 3; 2023: 1; 2024: 4; 2025: 1.

13 papers.

Sort:

  1. 2021Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymycited by 9
  2. 2021LegalNLP -- Natural Language Processing methods for the Brazilian Legal Languagecited by 6
  3. 2021Are Word Embedding Methods Stable and Should We Care About It?cited by 4
  4. 2022Using attention methods to predict judicial outcomescited by 1
  5. 2024A Small Claims Court for the NLP: Judging Legal Text Classification Strategies With Small Datasetscited by 1
  6. 2024NLP and Education: using semantic similarity to evaluate filled gaps in a large-scale Cloze test in the classroomcited by 1
  7. 2024Investigating Idiomaticity in Word Representationscited by 1
  8. 2025MaiBERT: A Pre-training Corpus and Language Model for Low-Resourced Maithili Languagecited by 1
  9. 2021Sense representations for Portuguese: experiments with sense embeddings and deep neural language modelscited by 0
  10. 2022Applying Word Embeddings to Measure Valence in Information Operations Targeting Journalists in Brazilcited by 0
  11. 2022Tracking environmental policy changes in the Brazilian Federal Official Gazettecited by 0
  12. 2023Beyond Accuracy: Measuring Representation Capacity of Embeddings to Preserve Structural and Contextual Informationcited by 0
1 more
  1. 2024Multi-level Product Category Prediction through Text Classificationcited by 0