PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Adaptation from partially supervised handwritten text transcriptions.
Nicolás Serrano, Daniel Pérez, Alberto Sanchis and Alfons Juan
In: ICMI-MLMI 2009, 2-6 Nov 2009, Cambridge, MA (USA).

Abstract

An effective approach to transcribe handwritten text documents is to follow an interactive-predictive paradigm in which both, the system is guided by the user, and the user is assisted by the system to complete the transcription task as efficiently as possible. This approach has been recently implemented in a system prototype called GIDOC, in which standard speech technology is adapted to handwritten text (line) images: HMM-based text image modelling, $n$-gram language modelling, and also confidence measures on recognised words. Confidence measures are used to assist the user in locating possible transcription errors, and thus validate system output after only supervising those (few) words for which the system is not highly confident. Here, we study the effect of using these partially supervised transcriptions on the adaptation of image and language models to the task.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:5666
Deposited By:Alfons Juan
Deposited On:08 March 2010