Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks
Published in
Brazilian Symposium in Information and Human La...(2017)External Links:
TL
TL;DR
Evaluating different word embedding models trained on a large Portuguese corpus, including both Brazilian and European variants, suggests that word analogies are not appropriate forword embedding evaluation; task-specific evaluations appear to be a better option.
Abstract
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.
References22 items
1
Visão Geral da Avaliação de Similaridade Semântica e Inferência Textual
2
Estudo de modelos de word embedding
3
Evaluating Word Embeddings Using a Representative Suite of Practical Tasks
4
Enriching Word Vectors with Subword Information
5