Skip to content

Research at St Andrews

A general technique to train language models on language models

Research output: Contribution to journalArticle

DOI

Author(s)

School/Research organisations

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.

Close

Details

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

    Research areas

  • GRAMMARS

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Regular transductions with MCFG input syntax

    Nederhof, M. J. & Vogler, H., 23 Sep 2019, Proceedings of the 14th International Conference on Finite-State Methods and Natural Language Processing. Maletti, A. & Vogler, H. (eds.). Dresden: Association for Computational Linguistics, p. 56-64 9 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  2. Hybrid grammars for parsing of discontinuous phrase structures and non-projective dependency structures

    Gebhardt, K., Nederhof, M. J. & Vogler, H., Sep 2017, In : Computational Linguistics. 43, 3, p. 465-520 56 p.

    Research output: Contribution to journalArticle

  3. A probabilistic model of Ancient Egyptian writing

    Nederhof, M. J. & Rahman, F., 1 Jul 2017, In : Journal of Language Modelling. 5, 1, p. 131-163

    Research output: Contribution to journalArticle

  4. A derivational model of discontinuous parsing

    Nederhof, M. J. & Yli-Jyra, A., 2017, Language and Automata Theory and Applications: 11th International Conference, LATA 2017, Umeå, Sweden, March 6-9, 2017, Proceedings. Drewes, F., Martin-Vide, C. & Truthe, B. (eds.). Cham: Springer, p. 299-310 (Lecture Notes in Computer Science (Theoretical Computer Science and General Issues); vol. 10168).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related by journal

  1. Hybrid grammars for parsing of discontinuous phrase structures and non-projective dependency structures

    Gebhardt, K., Nederhof, M. J. & Vogler, H., Sep 2017, In : Computational Linguistics. 43, 3, p. 465-520 56 p.

    Research output: Contribution to journalArticle

  2. Splittability of bilexical context-free grammars is undecidable

    Nederhof, M. J. & Satta, G., Dec 2011, In : Computational Linguistics. 37, 4, p. 867-879 13 p.

    Research output: Contribution to journalArticle

ID: 355702

Top