DMCA
Joint incremental disfluency detection and dependency parsing (2014)
Cached
Download Links
| Venue: | Transactions of the Association of Computational Linugistics (TACL |
| Citations: | 6 - 0 self |
BibTeX
@ARTICLE{Honnibal14jointincremental,
author = {Matthew Honnibal and Mark Johnson},
title = {Joint incremental disfluency detection and dependency parsing},
journal = {Transactions of the Association of Computational Linugistics (TACL},
year = {2014}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We present an incremental dependency parsing model that jointly performs disflu-ency detection. The model handles speech repairs using a novel non-monotonic tran-sition system, and includes several novel classes of features. For comparison, we evaluated two pipeline systems, us-ing 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. 1
Keyphrases
joint incremental disfluency detection dependency parsing novel non-monotonic tran-sition system incremental dependency parse accuracy linear time pipeline system disfluency detection joint model us-ing state-of-the-art disfluency detector speech repair disflu-ency detection several novel class
