Improved modeling of out-of-vocabulary words using morphological classes

Authors:
Thomas Müller;Hinrich Schütze
Affiliations:
University of Stuttgart, Germany;University of Stuttgart, Germany
Venue:
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Year:
2011

Citing 5
Cited 0

Class-based n-gram models of natural language

Computational Linguistics
Factored language models and generalized parallel backoff

NAACL-Short '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume of the Proceedings of HLT-NAACL 2003--short papers - Volume 2
Morph-based speech recognition and modeling of out-of-vocabulary words across languages

ACM Transactions on Speech and Language Processing (TSLP)
Modeling morphologically rich languages using split words and unstructured dependencies

ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
An automatic technique to include grammatical and morphological information in a trigram-based statistical language model

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a class-based language model that clusters rare words of similar morphology together. The model improves the prediction of words after histories containing out-of-vocabulary words. The morphological features used are obtained without the use of labeled data. The perplexity improvement compared to a state of the art Kneser-Ney model is 4% overall and 81% on unknown histories.