Abstract | ||
---|---|---|
Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection. This problem is amplified for models like Anchored Packed Trees (APTs), that take the grammatical type of a co-occurrence into account. We therefore introduce a novel form of distributional inference that exploits the rich type structure in APTs and infers missing data by the same mechanism that is used for semantic |
Year | DOI | Venue |
---|---|---|
2017 | 10.18653/v1/P17-2069 | PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 2 |
DocType | Volume | Citations |
Conference | abs/1704.06692 | 0 |
PageRank | References | Authors |
0.34 | 22 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thomas Kober | 1 | 5 | 0.74 |
Julie Weeds | 2 | 541 | 34.97 |
Jeremy Reffin | 3 | 43 | 1.82 |
David J. Weir | 4 | 840 | 83.84 |