Abstract | ||
---|---|---|
We show that under certain conditions, a language model can be trained on the basis of a second language model. The main instance of the technique trains a finite automaton on the basis of a probabilistic context-free grammar, such that the Kullback-Leibler distance between grammar and trained automaton is provably minimal. This is a substantial generalization of an existing algorithm to train an n-gram model on the basis of a probabilistic context-free grammar. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1162/0891201054223986 | Computational Linguistics |
Keywords | DocType | Volume |
finite automaton,language models,trained automaton,certain condition,main instance,general technique,existing algorithm,train language models,language model,substantial generalization,kullback-leibler distance,n-gram model,probabilistic context-free grammar | Journal | 31 |
Issue | ISSN | Citations |
2 | 0891-2017 | 11 |
PageRank | References | Authors |
0.83 | 13 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mark-jan Nederhof | 1 | 387 | 53.30 |