Abstract | ||
---|---|---|
Abstract. This paper explores the use of initial Stochastic Context-Free Gram-mars (SCFG) obtained from a treebank corpus for the learning of SCFG by means of estimation algorithms. A hybrid language model is defined as a combination of a word-based n-gram, which is used to capture the local relations between words, and a category-based SCFG with a word distribution into categories, which is de-fined to represent the long-term relations between these categories. Experiments on the UPenn Treebank corpus are reported. These experiments have been car-ried out in terms of the test set perplexity and the word error rate in a speech recognition experiment. |
Year | Venue | Keywords |
---|---|---|
2003 | ECML Workshop on Learning Contex-Free Grammars | speech recognition,word error rate,language model,stochastic context free grammar |
Field | DocType | Citations |
Rule-based machine translation,Perplexity,Context-free grammar,Computer science,Word error rate,Speech recognition,Synchronous context-free grammar,Natural language processing,Treebank,Artificial intelligence,Language model,Test set | Conference | 1 |
PageRank | References | Authors |
0.37 | 13 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Diego Linares | 1 | 24 | 4.54 |
José-Miguel Benedí | 2 | 318 | 29.43 |
Joan-Andreu Sánchez | 3 | 198 | 29.00 |