Joint incremental disfluency detection and dependency parsing

Matthew Honnibal, Mark Johnson

Research output: Contribution to journalArticlepeer-review

144 Downloads (Pure)

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.
Original languageEnglish
Pages (from-to)131-142
Number of pages12
JournalTransactions of the Association for Computational Linguistics
Volume2
Issue number1
Publication statusPublished - 2014

Bibliographical note

Copyright the Publisher 2014. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Fingerprint

Dive into the research topics of 'Joint incremental disfluency detection and dependency parsing'. Together they form a unique fingerprint.

Cite this