Consistency of Stochastic Context-Free Grammars From Probabilistic Estimation Based on Growth Transformations

  title={Consistency of Stochastic Context-Free Grammars From Probabilistic Estimation Based on Growth Transformations},
  author={Joan-Andreu S{\'a}nchez and Jos{\'e}-Miguel Bened{\'i}},
  journal={IEEE Trans. Pattern Anal. Mach. Intell.},
An important problem related to the probabilistic estimation of Stochastic Context-Free Grammars (SCFGs) is guaranteeing the consistency of the estimated model. This problem was considered in 3, 14] and studied in 10, 4] for unambiguous SCFGs only, when the probabilistic distributions were estimated by the relative frequencies in a training sample. In this work, we extend this result by proving that the property of consistency is guaranteed for all SCFGs without restrictions, when the… CONTINUE READING

From This Paper

Topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 14 references

An inequality and associated maximization technique in statistical es- timation for probabilistic functions of markov processes. Inequalities

  • L. E. Baum
  • 1972
Highly Influential
10 Excerpts

Stochastic grammars and pattern recognition

  • H. Ney
  • Speech Recognition and Understanding. Recent…
  • 1992
Highly Influential
7 Excerpts

Trainable grammars for speech recognition

  • J. K. Baker
  • In Klatt and Wolf, editors,
  • 1979
Highly Influential
5 Excerpts

Gramáticas incontextuales probabilísticas consist- entes

  • J. A. Sánchez, J. M. Benedí
  • Technical Report DSIC-II/20/96, Departamento de…
  • 1996
1 Excerpt

The estimation of stochastic context-free grammars using the inside-outside algorithm

  • K. Lari, S. J. Young
  • Computer, Speech and Language,
  • 1990
2 Excerpts

Similar Papers

Loading similar papers…