Efficient sampling and feature selection in whole sentence maximum entropy language models

@article{Chen1999EfficientSA,
  title={Efficient sampling and feature selection in whole sentence maximum entropy language models},
  author={Stanley F. Chen and Ronald Rosenfeld},
  journal={1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)},
  year={1999},
  volume={1},
  pages={549-552 vol.1}
}
Conditional maximum entropy models have been successfully applied to estimating language model probabilities of the form P(w|h), but are often to demanding computationally. Furthermore, the conditional framework does not lend itself to expressing global sentential phenomena. We have previously introduced a non-conditional maximum entropy language model which directly models the probability of an entire sentence or utterance. The model treats each utterance as a "bag of features", where features… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 32 CITATIONS

Whole Sentence Neural Language Models

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Audio-linguistic Embeddings for Spoken Sentences

VIEW 1 EXCERPT
CITES BACKGROUND

Biological terms boundary identification by maximum entropy model

VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 17 REFERENCES

Just-in-time language modelling

  • Adam Berger, Robert Miller
  • Computer Science
  • Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)
  • 1998
VIEW 2 EXCERPTS

A whole sentence maximum entropy language model

  • Roni Rosenfeld
  • Computer Science
  • 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings
  • 1997
VIEW 2 EXCERPTS

A maximum entropy approach to adaptive statistical language modelling

VIEW 2 EXCERPTS

Improved backing-off for M-gram language modeling

VIEW 1 EXCERPT

Inducing Features of Random Fields

VIEW 3 EXCERPTS

Kneser . On structuring probabilistic dependences in stochastic language modeling

  • U. Essen H. Ney, R.
  • Computer , Speech , and Language
  • 1994