Paper: Combining Punctuation and Disfluency Prediction: An Empirical Study

ACL ID D14-1013
Title Combining Punctuation and Disfluency Prediction: An Empirical Study
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

Punctuation prediction and disfluency pre- diction can improve downstream natural language processing tasks such as ma- chine translation and information extrac- tion. Combining the two tasks can poten- tially improve the efficiency of the over- all pipeline system and reduce error prop- agation. In this work 1 , we compare var- ious methods for combining punctuation prediction (PU) and disfluency prediction (DF) on the Switchboard corpus. We com- pare an isolated prediction approach with a cascade approach, a rescoring approach, and three joint model approaches. For the cascade approach, we show that the soft cascade method is better than the hard cascade method. We also use the cas- cade models to generate an n-best list, use the bi-directional cascade models to per- form rescoring, and ...