Sciweavers

Share
EMNLP
2011

Training dependency parsers by jointly optimizing multiple objectives

8 years 2 months ago
Training dependency parsers by jointly optimizing multiple objectives
We present an online learning algorithm for training parsers which allows for the inclusion of multiple objective functions. The primary example is the extension of a standard supervised parsing objective function with additional loss-functions, either based on intrinsic parsing quality or task-specific extrinsic measures of quality. Our empirical results show how this approach performs for two dependency parsing algorithms (graph-based and transition-based parsing) and how it achieves increased performance on multiple target tasks including reordering for machine translation and parser adaptation.
Keith Hall, Ryan T. McDonald, Jason Katz-Brown, Mi
Added 20 Dec 2011
Updated 20 Dec 2011
Type Journal
Year 2011
Where EMNLP
Authors Keith Hall, Ryan T. McDonald, Jason Katz-Brown, Michael Ringgaard
Comments (0)
books