Corpus ID: 1541076

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

@inproceedings{Hartmann2017PortugueseWE,
  title={Portuguese Word Embeddings: Evaluating on Word Analogies and Natural Language Tasks},
  author={N. Hartmann and Erick Rocha Fonseca and C. Shulby and Marcos Vin{\'i}cius Treviso and J{\'e}ssica S. Rodrigues and S. Alu{\'i}sio},
  booktitle={STIL},
  year={2017}
}
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. [...] Key Method 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…Expand
Generating Sense Embeddings for Syntactic and Semantic Analogy for Portuguese
Learning Word Vectors for 157 Languages
isiZulu Word Embeddings
Assessing Lexical-Semantic Regularities in Portuguese Word Embeddings
Word Embedding Evaluation in Downstream Tasks and Semantic Analogies
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 23 REFERENCES
Enriching Word Vectors with Subword Information
Evaluating word embeddings and a revised corpus for part-of-speech tagging in Portuguese
...
1
2
3
...