Cooccurrence smoothing for stochastic language modelingAcoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on, Vol. 1 (1992), pp. 161-164 vol.1.
|
Reviews
[Write a review of this article]
There are no reviews of this article
Find related articles from these CiteULike users
Find related articles with these CiteULike tags
摘要Training corpora for stochastic language models are virtually always too small for maximum-likelihood estimation, so smoothing the models is of great importance. The authors derive the cooccurrence smoothing technique for stochastic language modeling and give experimental evidence for its validity. Using word-bigram language models, cooccurrence smoothing improved the test-set perplexity by 14% on a German 100000-word text corpus and by 10% on an English 1-million word corpus
BibTeX record
RIS record