Improved Modeling of Out-Of-Vocabulary Words Using Morphological Classes

Improved Modeling of Out-Of-Vocabulary Words Using Morphological Classes

Cached

Download Links

by Thomas Müller , Hinrich Schütze

BibTeX

@MISC{Müller_improvedmodeling,
    author = {Thomas Müller and Hinrich Schütze},
    title = {Improved Modeling of Out-Of-Vocabulary Words Using Morphological Classes},
    year = {}
}

Bookmark

OpenURL

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 outof-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. 1

Citations

647	Class-based n-gram models of natural language - Brown, deSouza, et al. - 1992
586	Probabilistic part-of-speech tagging using decision trees - Schmid - 1994
78	Factored language models and generalized parallel backoff - Bilmes, Kirchhoff - 2003
30	A simpler, intuitive approach to morpheme induction - Keshava, Pitler - 2006
28	Comparison of part-of-speech and automatically derived category-based language models for speech recognition - Niesler, Whittaker, et al. - 1998
25	Morphology-based language modeling for Arabic speech recognition - Vergyri, Kirchhoff, et al. - 2004
13	A fast algorithm for deleted interpolation - Bahl, Brown, et al. - 1991
8	An automatic technique to include grammatical and morphological information in a trigram-based statistical language model - Maltese, Mancini - 1992
4	Teemu Hirsimäki, Mikko Kurimo, Antti Puurula, Janne Pylkkönen, Vesa Siivola, Matti Varjokallio, Ebru Arisoy, Murat Saraçlar, and Andreas Stolcke. 2007. Morph-based speech recognition and modeling of out-of-vocabulary words across languages - Creutz