Name
Abstract | ||
|---|---|---|
Nearly all work in unsupervised grammar induction aims to induce unlabeled dependency trees from gold part-of-speech-tagged text. These clean linguistic classes provide a very important, though unrealistic, inductive bias. Conversely, induced clusters are very noisy. We show here, for the first time, that very limited human supervision (three frequent words per cluster) may be required to induce labeled dependencies from automatically induced word clusters. |
Year | Venue | Field |
|---|---|---|
2015 | PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL) AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (IJCNLP), VOL 2 | Inductive bias,Grammar induction,Computer science,Minimal supervision,Artificial intelligence,Natural language processing |
DocType | Volume | Citations |
Conference | P15-2 | 3 |
PageRank | References | Authors |
0.38 | 18 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yonatan Bisk | 1 | 196 | 17.54 |
| Christos Christodoulopoulos | 2 | 74 | 9.67 |
| Julia Hockenmaier | 3 | 1782 | 114.23 |