Draft report: Document Analysis with Transducers

In retrospect, I believe that this early draft is a much better document than the published papers discussing the powerful Graph Transformer Networks.

Abstract: We present here a general architecture for building Automatic Document Analysis Systems. This architecture is composed of a succession of modules transforming graphs describing lower-level hypotheses on the documents into graphs describing higher level hypotheses. This architecture generalizes techniques used in Neural Networks, Optical Character Recognition, Natural Language Processing and Speech Recognition.

Léon Bottou, Yoshua Bengio and Yann LeCun: Document Analysis with Transducers, Draft technical report, July 1996.

transducer-1996.djvu transducer-1996.pdf transducer-1996.ps.gz

@misc{bottou-1996,
  author = {Bottou, L\'{e}on and Bengio, Yoshua and {LeCun}, Yann},
  title = {Document Analysis with Transducers},
  year = {1996},
  month = {July},
  optnote = {Tech report available on http://leon.bottou.com/publications},
  url = {http://leon.bottou.org/papers/bottou-1996},
}