Sciweavers

Share
ACL
2009

Concise Integer Linear Programming Formulations for Dependency Parsing

8 years 7 months ago
Concise Integer Linear Programming Formulations for Dependency Parsing
We formulate the problem of nonprojective dependency parsing as a polynomial-sized integer linear program. Our formulation is able to handle non-local output features in an efficient manner; not only is it compatible with prior knowledge encoded as hard constraints, it can also learn soft constraints from data. In particular, our model is able to learn correlations among neighboring arcs (siblings and grandparents), word valency, and tendencies toward nearlyprojective parses. The model parameters are learned in a max-margin framework by employing a linear programming relaxation. We evaluate the performance of our parser on data in several natural languages, achieving improvements over existing state-of-the-art methods.
André L. Martins, Noah A. Smith, Eric P. Xi
Added 16 Feb 2011
Updated 16 Feb 2011
Type Journal
Year 2009
Where ACL
Authors André L. Martins, Noah A. Smith, Eric P. Xing
Comments (0)
books