GloVe: Global Vectors for Word Representation

5 Conclusion

1. How did Pennington et al. position GloVe in the count-based vs prediction-based debate?
   The two families aren’t fundamentally different, since both probe the same co-occurrence statistics; count-based methods capture global statistics more efficiently. GloVe uses count data while capturing the linear substructures of log-bilinear prediction models like word2vec.
   • Pennington et al., 2014, GloVe (Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)), §5, p. 1541