Title | ||
---|---|---|
Matrix Factorization Using Window Sampling And Negative Sampling For Improved Word Representations |
Abstract | ||
---|---|---|
In this paper, we propose LexVec, a new method for generating distributed word representations that uses low-rank, weighted factorization of the Positive Point-wise Mutual Information matrix via stochastic gradient descent, employing a weighting scheme that assigns heavier penalties for errors on frequent co-occurrences while still accounting for negative co-occurrence. Evaluation on word similarity and analogy tasks shows that LexVec matches and often outperforms state-of-the-art methods on many of these tasks. |
Year | Venue | DocType |
---|---|---|
2016 | PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2016), VOL 2 | Conference |
Volume | Citations | PageRank |
abs/1606.00819 | 13 | 0.63 |
References | Authors | |
18 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alexandre Salle | 1 | 24 | 2.66 |
Marco Idiart | 2 | 84 | 11.23 |
Aline Villavicencio | 3 | 20 | 3.41 |