GloVe: Global Vectors for Word Representation

4.3 Results

1. How did GloVe do on word analogies?
   75.0% overall with 300-dimensional vectors on 42B tokens; on 6B tokens 71.7% vs 69.1% for skip-gram and 65.7% for CBOW trained by the authors with word2vec. It often beat other models with smaller vectors and corpora; SVD baselines didn’t scale to the larger corpus.
   • Pennington et al., 2014, GloVe (Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)), §4.3, pp. 1539–1540
2. How did GloVe vectors do on word similarity and NER?
   Best on the similarity sets, beating the word2vec CBOW vectors trained on 100B words with less than half the data. As CRF features for NER, best on all metrics except the CoNLL test set, where HPCA was slightly better.
   • Pennington et al., 2014, GloVe (Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)), §4.3, pp. 1539–1540