Abstract | ||
---|---|---|
We simulate first- and second-order context overlap and show that Skip-Gram with Negative Sampling is similar to Singular Value Decomposition in capturing second-order co-occurrence information, while Pointwise Mutual Information is agnostic to it. We support the results with an empirical study finding that the models react differently when provided with additional second-order information. Our findings reveal a basic property of Skip-Gram with Negative Sampling and point towards an explanation of its success on a variety of tasks. |
Year | DOI | Venue |
---|---|---|
2019 | 10.18653/v1/w19-4803 | BLACKBOXNLP WORKSHOP ON ANALYZING AND INTERPRETING NEURAL NETWORKS FOR NLP AT ACL 2019 |
DocType | Volume | Citations |
Journal | abs/1906.02479 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dominik Schlechtweg | 1 | 2 | 7.85 |
Cennet Oguz | 2 | 0 | 0.34 |
Sabine Schulte im Walde | 3 | 440 | 65.65 |