A general technique to train language models on language models

DOI10.1162/0891201054223986MaRDI QIDQ3225429zbMATH OpenOpenAlexFDO

Authors Mark-Jan Nederhof

Publication date 20 March 2012

Published in Computational Linguistics (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Full work available at URL https://doi.org/10.1162/0891201054223986

Mathematics Subject Classification ID

Grammars and rewriting systems (68Q42) Formal languages and automata (68Q45)

Recommendations

• 10.1162/153244303322533223
• Finite automata for compact representation of language models in NLP
• Training probabilistic context-free grammars as hidden Markov models
• Probabilistic k-testable tree languages
• The use of the maximum likelihood criterion in language modelling

Cites work

• On multiple context-free grammars
• Probabilistic grammars and automata

Cited in

(5)

• Regular Approximation of Weighted Linear Nondeleting Context-Free Tree Languages
• Regular Approximation of Weighted Linear Context-Free Tree Languages
• Learning context sensitive languages with LSTM trained with Kalman filters
• Computational and Information Science
• Computation of distances for regular and context-free probabilistic languages

This page was built for publication: A general technique to train language models on language models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3225429)