Paper: Online Learning for Deterministic Dependency Parsing

ACL ID D07-1124
Title Online Learning for Deterministic Dependency Parsing
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2007
  • Prashanth Mannem (International Institute of Information Technology, Hyderabad India)

Deterministic parsing has emerged as an ef- fective alternative for complex parsing algo- rithms which search the entire search space to get the best probable parse tree. In this pa- per, we present an online large margin based training framework for deterministic pars- ing using Nivre’s Shift-Reduce parsing al- gorithm. Online training facilitates the use of high dimensional features without cre- ating memory bottlenecks unlike the popu- lar SVMs. We participated in the CoNLL Shared Task-2007 and evaluated our system for ten languages. We got an average multi- lingual labeled attachment score of 74.54 % (with 65.50% being the average and 80.32% the highest) and an average multilingual un- labeled attachment score of 80.30% (with 71.13% being the average and 86.55% the highest).