Robust cross-domain disfluency detection with pattern match networks
Computation and Language
2018-11-20 v1 Artificial Intelligence
Abstract
In this paper we introduce a novel pattern match neural network architecture that uses neighbor similarity scores as features, eliminating the need for feature engineering in a disfluency detection task. We evaluate the approach in disfluency detection for four different speech genres, showing that the approach is as effective as hand-engineered pattern match features when used on in-domain data and achieves superior performance in cross-domain scenarios.
Cite
@article{arxiv.1811.07236,
title = {Robust cross-domain disfluency detection with pattern match networks},
author = {Vicky Zayats and Mari Ostendorf},
journal= {arXiv preprint arXiv:1811.07236},
year = {2018}
}
Comments
This paper was submitted to EMNLP 2018 and was rejected. Our EMNLP submission is posted here to establish concurrency with "Disfluency Detection using Auto-Correlational Neural Networks" by P. Lou, P. Anderson, M. Johnson which was submitted to EMNLP at the same time