Shared Context Probabilistic Transducers

Abstract

Recently, a model for supervised learning of probabilistic transduc(cid:173) ers represented by suffix trees was introduced. However, this algo(cid:173) rithm tends to build very large trees, requiring very large amounts of computer memory. In this paper, we propose anew, more com(cid:173) pact, transducer model in which one shares the parameters of distri(cid:173) butions associated to contexts yielding similar conditional output distributions . We illustrate the advantages of the proposed algo(cid:173) rithm with comparative experiments on inducing a noun phrase recogmzer.

Cite

Text

Bengio et al. "Shared Context Probabilistic Transducers." Neural Information Processing Systems, 1997.

Markdown

[Bengio et al. "Shared Context Probabilistic Transducers." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/bengio1997neurips-shared/)

BibTeX

@inproceedings{bengio1997neurips-shared,
  title     = {{Shared Context Probabilistic Transducers}},
  author    = {Bengio, Yoshua and Bengio, Samy and Isabelle, Jean-Franc and Singer, Yoram},
  booktitle = {Neural Information Processing Systems},
  year      = {1997},
  pages     = {409-415},
  url       = {https://mlanthology.org/neurips/1997/bengio1997neurips-shared/}
}