Results 1 
3 of
3
Combination Of NGrams And Stochastic ContextFree Grammars For Language Modeling
 International conference on computational linguistics (COLINA CL
, 2000
"... This paper describes a hybrid proposal to combine ngrams and Stochastic ContextFree Grammars (SCFGs) for language modeling. A classical ngram model is used to capture the local relations between words, while a stochastic grammatical model is considered to represent the longterm relations between ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
This paper describes a hybrid proposal to combine ngrams and Stochastic ContextFree Grammars (SCFGs) for language modeling. A classical ngram model is used to capture the local relations between words, while a stochastic grammatical model is considered to represent the longterm relations between syntactical structures. In order to dene this grammatical model, which will be used on largevocabulary complex tasks, a categorybased SCFG and a probabilistic model of word distribution in the categories have been proposed. Methods for learning these stochastic models for complex tasks are described, and algorithms for computing the word transition probabilities are also presented. Finally, experiments using the Penn Treebank corpus improved by 30% the test set perplexity with regard to the classical ngram models.
Combination of Estimation Algorithms and Grammatical Inference Techniques to Learn Stochastic ContextFree Grammars
, 2000
"... Some of the most widelyknown methods to obtain Stochastic ContextFree Grammars (SCFGs) are based on estimation algorithms. ALl of these algorithms maximize a cetrain criterion function from a training sample... ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
Some of the most widelyknown methods to obtain Stochastic ContextFree Grammars (SCFGs) are based on estimation algorithms. ALl of these algorithms maximize a cetrain criterion function from a training sample...
Probabilistic Estimation Of Stochastic ContextFree Grammars From The KBest Derivations
, 1999
"... The use of the InsideOutside (IO) algorithm for the estimation of the probability distributions of Stochastic ContextFree Grammars in Language Modeling is restricted due to the time complexity per iteration and the large number of iterations that it needs to converge. ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
The use of the InsideOutside (IO) algorithm for the estimation of the probability distributions of Stochastic ContextFree Grammars in Language Modeling is restricted due to the time complexity per iteration and the large number of iterations that it needs to converge.