Search Results for "regular expression"

Tesseract OCR is an open source, highly accurate image to text converter. Nevertheless, Tesseract OCR provides only command line interface. JATI is just another interface to the Tesseract OCR engine, providing GUI interface to convert an image to text. It can do batch conversion, including converting only portion of the image into text.

For general processing of voice queries we developed a text parsing library named 'Rootvole' that can be used to match text with semantic concepts. The algorithm was implemented in Java and can be described as a form of a parsing expression grammar, where we generate the expressions to be detected beforehand by regular expressions and store them in a vocabulary. The central class is the parser class, which is instantiated as a series of vocabularies, simple text lists that describe tokens and synonyms, and value descriptors. It's meant as a lightweight alternative to "real" NLP (natural language processing).

Created by Conversive, the Verbot (Verbally Enhanced Software Robot) is based on more than 10 years of AI experience and development. Using XML and .NET architecture, the Verbots SDK allows you to create engaging interactive personalities.