Robust cross-domain disfluency detection with pattern match networks
Preprint
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.Keywords
All Related Versions
This publication has 2 references indexed in Scilit:
- Disfluency Detection Using a Bidirectional LSTM2016
- Joint Incremental Disfluency Detection and Dependency ParsingTransactions of the Association for Computational Linguistics, 2014