Sciweavers

Share
AAAI
2015

Learning Greedy Policies for the Easy-First Framework

3 years 7 months ago
Learning Greedy Policies for the Easy-First Framework
Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a learned greedy policy (action scoring function) to make easy decisions first, which constrains the remaining decisions and makes them easier. We formulate greedy policy learning in the Easy-first approach as a novel non-convex optimization problem and solve it via an efficient Majorization Minimization (MM) algorithm. Results on within-document coreference and cross-document joint entity and event coreference tasks demonstrate that the proposed approach achieves statistically significant performance improvement over existing training regimes for Easy-first and is less susceptible to overfitting.
Jun Xie, Chao Ma, Janardhan Rao Doppa, Prashanth M
Added 27 Mar 2016
Updated 27 Mar 2016
Type Journal
Year 2015
Where AAAI
Authors Jun Xie, Chao Ma, Janardhan Rao Doppa, Prashanth Mannem, Xiaoli Z. Fern, Thomas G. Dietterich, Prasad Tadepalli
Comments (0)
books