Glove: Global Vectors for Word Representation

Citations Over TimeTop 1% of 2014 papers

Abstract

Recent methods for learning vector space representations of words have succeeded in capturing fine-grained semantic and syntactic regularities using vector arithmetic, but the origin of these regularities has remained opaque. We analyze and make explicit the model properties needed for such regularities to emerge in word vectors. The result is a new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods. Our model efficiently leverages statistical information by training only on the nonzero elements in a word-word cooccurrence matrix, rather than on the entire sparse matrix or on individual context windows in a large corpus. The model produces a vector space with meaningful substructure, as evidenced by its performance of 75% on a recent word analogy task. It also outperforms related models on similarity tasks and named entity recognition.

Related Papers

• → Women’s Representation in Argentine National and Subnational Governments(2018)24 cited
• → Elections and Representation in Local Government: A Victorian Case Study(2004)22 cited
• → Prelude to a Theory of Musical Representation(2017)1 cited
• → Ten Fun Word‐Building Activities(2008)
• → Faculty Opinions recommendation of Statistical laws governing fluctuations in word use from word birth to word death.(2012)