A minimum description length approach to grammar inference

@inproceedings{Grnwald1995AMD,
  title={A minimum description length approach to grammar inference},
  author={Peter Gr{\"u}nwald},
  booktitle={Learning for Natural Language Processing},
  year={1995}
}
We describe a new abstract model for the computational learning of grammars. The model deals with a learning process in which an algorithm is given an input of a large set of training sentences that belong to some unknown grammar. The algorithm then tries to infer this grammar. Our model is based on the well-known Minimum Description Length Principle. It is quite close to, but more general than several other existing approaches. We have shown that one of these approaches (based on n-gram… CONTINUE READING

From This Paper

Topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 12 references

Automatic grammar induction using the MDL Principle. Master's thesis

  • P D Gr, Unwald
  • Automatic grammar induction using the MDL…
  • 1994

Vitt anyi. An introduction to Kolmogorov complexity and its applications

  • M Li
  • Vitt anyi. An introduction to Kolmogorov…
  • 1993

Classbased n-gram models of natural language

  • P F Brown, V J Della Pietra, P V Desouza, J C Lai, R L Mercer
  • Computational Linguistics
  • 1992

A hybrid approach to the automatic learning of linguistic categories

  • S Finch, N Chater
  • AISB Quarterly
  • 1991

Language acquisition, data compression, and generalization. Language and Communication

  • J G Woll
  • Language acquisition, data compression, and…
  • 1982

Information Theory and Reliable Communication

  • R G Gallager
  • Information Theory and Reliable Communication
  • 1968

Computational Analysis of Present Day American English

  • H Ku Cera, W Francis
  • Computational Analysis of Present Day American…
  • 1967

Similar Papers

Loading similar papers…