Connected Text Recognition Using Layered HMMs and Token Passing

Details Connected Text Recognition Using Layered HMMs and Token Passing Connected Text Recognition Using Layered HMMs and Token Passing

1996-07-31

arxiv.org/abs/cmp-lg/9607036v1

Proceedings of NeMLaP-2

Computer Science

Computation and Language

12 pages, LaTeX format, 3 encapsulated Postscript figures, uses nemlap.sty

Scientific paper

We present a novel approach to lexical error recovery on textual input. An advanced robust tokenizer has been implemented that can not only correct spelling mistakes, but also recover from segmentation errors. Apart from the orthographic considerations taken, the tokenizer also makes use of linguistic expectations extracted from a training corpus. The idea is to arrange Hidden Markov Models (HMM) in multiple layers where the HMMs in each layer are responsible for different aspects of the processing of the input. We report on experimental evaluations with alternative probabilistic language models to guide the lexical error recovery process.

Affiliated with

Also associated with

No associations

Rating

Connected Text Recognition Using Layered HMMs and Token Passing does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Connected Text Recognition Using Layered HMMs and Token Passing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Connected Text Recognition Using Layered HMMs and Token Passing will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-588361