Skip to main navigation menu Skip to main content Skip to site footer

Joint Incremental Disfluency Detection and Dependency Parsing

Abstract

We present an incremental dependency parsing model that jointly performs disfluency detection. The model handles speech repairs using a novel non-monotonic transition system, and includes several novel classes of features. For comparison, we evaluated two pipeline systems, using state-of-the-art disfluency detectors. The joint model performed better on both tasks, with a parse accuracy of 90.5% and 84.0% accuracy at disfluency detection. The model runs in expected linear time, and processes over 550 tokens a second. 

PDF (Presented at ACL 2014)

Author Biography

Matthew Honnibal

Post-doctoral Researcher

Department of Computing

Macquarie University

Mark Johnson

Professor of Language Sciences (CORE)
Director, Centre for Language Sciences (CLaS)

Department of Computing

Macquarie University