Paper: Joint Parsing and Disfluency Detection in Linear Time

ACL ID D13-1013
Title Joint Parsing and Disfluency Detection in Linear Time
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013
Authors

We introduce a novel method to jointly parse and detect disfluencies in spoken utterances. Our model can use arbitrary features for pars- ing sentences and adapt itself with out-of- domain data. We show that our method, based on transition-based parsing, performs at a high level of accuracy for both the parsing and disfluency detection tasks. Additionally, our method is the fastest for the joint task, running in linear time.