PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Balancing error and supervision effort in interactive-predictive handwriting recognition.
Nicolás Serrano, Alberto Sanchis and Alfons Juan
In: 14th Int. Conf. on Intelligent User Interfaces, 7-10 Feb 2010, China.

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 modeling, $n$-gram language modeling, and also confidence measures on recognized 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. However, a certain degree of supervision is required for proper model adaptation from partially supervised transcriptions. Here, we propose a simple yet effective method to find an optimal balance between recognition error and supervision effort.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Natural Language Processing
ID Code:5668
Deposited By:Alfons Juan
Deposited On:08 March 2010