Paper: A generative re-ranking model for dependency parsing

ACL ID W09-3839
Title A generative re-ranking model for dependency parsing
Venue International Conference on Parsing Technologies
Session Main Conference
Year 2009
Authors

We propose a framework for dependency parsing based on a combination of dis- criminative and generative models. We use a discriminative model to obtain a k- best list of candidate parses, and subse- quently rerank those candidates using a generative model. We show how this ap- proach allows us to evaluate a variety of generative models, without needing differ- ent parser implementations. Moreover, we present empirical results that show a small improvement over state-of-the-art depen- dency parsing of English sentences.