learn.ifs.name

GloVe: Global Vectors for Word Representation

Pennington et al., 2014, GloVe (Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP))

Subscriber deck — free during early access

1 cards in “4.7 Model Analysis: Comparison with word2vec” · whole deck

4.7 Model Analysis: Comparison with word2vec

  1. How did GloVe compare with word2vec at equal training time?
    With the same corpus, vocabulary, window size and training time (GloVe iterations vs word2vec negative samples), GloVe was consistently better, reaching better results faster. word2vec got worse with more than about 10 negative samples.
    • Pennington et al., 2014, GloVe (Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)), §4.7, pp. 1540–1541

Source

  • Jeffrey Pennington, Richard Socher and Christopher D. Manning. 2014. GloVe: Global Vectors for Word Representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543. doi:10.3115/v1/D14-1162 https://aclanthology.org/D14-1162/