Greed Is Good If Randomized: New Inference for Dependency Parsing

Greed Is Good If Randomized: New Inference for Dependency Parsing

Dependency parsing with high-order features results in a provably hard decoding problem. A lot of work has gone into developing powerful optimization methods for solving these combinatorial problems. In contrast, we explore, analyze, and demonstrate that a substantially simpler randomized greedy inf...

Full description

Bibliographic Details
Main Authors: Zhang, Yuan (Contributor), Lei, Tao (Contributor), Barzilay, Regina (Contributor), Jaakkola, Tommi S. (Contributor)
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
Format: Article
Language:English
Published: 2015-11-09T13:55:41Z.
Subjects:
Article
Online Access:Get fulltext

Internet

Get fulltext

Similar Items