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

arXiv: https://arxiv.org/abs/1708.06025 · HTML: https://mlsanity.com/paper/1708.06025/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2017.

## Built on by (most cited first, 13 of 13)

- [Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy](https://mlsanity.com/paper/2106.13553/) (2021)
- [LegalNLP -- Natural Language Processing methods for the Brazilian Legal Language](https://mlsanity.com/paper/2110.15709/) (2021)
- [Are Word Embedding Methods Stable and Should We Care About It?](https://mlsanity.com/paper/2104.08433/) (2021)
- [Using attention methods to predict judicial outcomes](https://mlsanity.com/paper/2207.08823/) (2022)
- [A Small Claims Court for the NLP: Judging Legal Text Classification Strategies With Small Datasets](https://mlsanity.com/paper/2409.05972/) (2024)
- [NLP and Education: using semantic similarity to evaluate filled gaps in a large-scale Cloze test in the classroom](https://mlsanity.com/paper/2411.01280/) (2024)
- [Investigating Idiomaticity in Word Representations](https://mlsanity.com/paper/2411.02610/) (2024)
- [MaiBERT: A Pre-training Corpus and Language Model for Low-Resourced Maithili Language](https://mlsanity.com/paper/2509.15048/) (2025)
- [Sense representations for Portuguese: experiments with sense embeddings and deep neural language models](https://mlsanity.com/paper/2109.00025/) (2021)
- [Applying Word Embeddings to Measure Valence in Information Operations Targeting Journalists in Brazil](https://mlsanity.com/paper/2201.02257/) (2022)
- [Tracking environmental policy changes in the Brazilian Federal Official Gazette](https://mlsanity.com/paper/2202.10221/) (2022)
- [Beyond Accuracy: Measuring Representation Capacity of Embeddings to Preserve Structural and Contextual Information](https://mlsanity.com/paper/2309.11294/) (2023)
- [Multi-level Product Category Prediction through Text Classification](https://mlsanity.com/paper/2403.01638/) (2024)

## 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.