DTIC ADA633691: Tag assisted Sentence Confabulation for pdf

DTIC ADA633691: Tag assisted Sentence Confabulation for

More Book Details

Description of the Book:

Autonomous and intelligent recognition of printed or hand-written text image is one of the key features to achieve situational awareness. A neuromorphic model based intelligent text recognition (ITR) system has been developed in our previous work, which recognizes texts based on word level and sentence level context represented by statistical information of characters and words. While quite effective, sometimes the existing ITR system still generates results that are grammatically incorrect because it ignores semantic and syntactic properties of sentences. In this work, we improve the accuracy of the existing ITR system by incorporating parts-of- speech tagging into the text recognition procedure. Our experimental results show that the tag-assisted text recognition improves sentence level success rate by 33% in average

• Creator/s: Defense Technical Information Center
• Date: 1/1/2012
• Year: 2012
• Book Topics/Themes: DTIC Archive, , SYRACUSE UNIV NY, *PATTERN RECOGNITION, *TEXT PROCESSING, ACCURACY, CLASSIFICATION, COMPUTATIONAL LINGUISTICS, EXPERIMENTAL DESIGN, LEXICOGRAPHY, MATHEMATICAL MODELS, PROBABILITY, SEMANTICS, SITUATIONAL AWARENESS, SPEECH, STATISTICAL DATA, SYMPOSIA, SYNTAX, WORDS(LANGUAGE

An excerpt captured from the PDF book