Abstract
We describe an online learning dependency parser for the CoNLL-X Shared Task, based on the bottom-up projective algorithm of Eisner (2000). We experiment with a large feature set that models: the tokens involved in dependencies and their immediate context, the surface-text distance between tokens, and the syntactic context dominated by each dependency. In experiments, the treatment of multilingual information was totally blind.
Original language | English (US) |
---|---|
Pages | 181-185 |
Number of pages | 5 |
State | Published - 2006 |
Externally published | Yes |
Event | 10th Conference on Computational Natural Language Learning, CoNLL 2006 - New York City, United States Duration: Jun 8 2006 → Jun 9 2006 |
Conference
Conference | 10th Conference on Computational Natural Language Learning, CoNLL 2006 |
---|---|
Country/Territory | United States |
City | New York City |
Period | 6/8/06 → 6/9/06 |
ASJC Scopus subject areas
- Artificial Intelligence
- Human-Computer Interaction
- Linguistics and Language