A general technique to train language models on language models

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)

Abstract

We show that under certain conditions, a language model can be trained oil 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.

Original languageEnglish
Pages (from-to)173-185
Number of pages13
JournalComputational Linguistics
Volume31
Issue number2
DOIs
Publication statusPublished - Jun 2005

Keywords

  • GRAMMARS

Fingerprint

Dive into the research topics of 'A general technique to train language models on language models'. Together they form a unique fingerprint.

Cite this