Joint Parsing and Disfluency Detection in Linear Time
Mohammad Sadegh Rasooli, Joel Tetreault · 2013
We introduce a novel method to jointly parse and detect disfluencies in spoken utterances.Our model can use arbitrary features for parsing sentences and adapt itself with out-ofdomain 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.