Abstract
In this work we learn clusters of contextual annotations for non-terminals in the Penn Treebank. Perhaps the best way to think about this problem is to contrast our work with that of Klein and Manning (2003). That research used tree-transformations to create various grammars with different contextual annotations on the non-terminals. These grammars were then used in conjunction with a CKY parser. The authors explored the space of different annotation combinations by hand. Here we try to automate the process- to learn the "right" combination automatically. Our results are not quite as good as those carefully created by hand, but they are close (84.8 vs 85.7).
| Original language | English |
|---|---|
| Title of host publication | EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing |
| Place of Publication | Stroudsburg, PA |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 301-307 |
| Number of pages | 7 |
| ISBN (Print) | 1932432736, 9781932432732 |
| Publication status | Published - Jul 2006 |
| Externally published | Yes |
| Event | 11th Conference on Empirical Methods in Natural Language Proceessing, EMNLP 2006, Held in Conjunction with COLING/ACL - 2006 - Sydney, Australia Duration: 22 Jul 2006 → 23 Jul 2006 |
Other
| Other | 11th Conference on Empirical Methods in Natural Language Proceessing, EMNLP 2006, Held in Conjunction with COLING/ACL - 2006 |
|---|---|
| Country/Territory | Australia |
| City | Sydney |
| Period | 22/07/06 → 23/07/06 |