Natural language recognition using distributed processing

Abstract

A method and system for computer-based recognition of natural language data. The method is implemented on a distributed computer network and includes obtaining natural language data, such as digital ink handwriting, using an input device 415, receiving the natural language data on a server 430 via a network, processing the natural language data using a recognizer 440 residing on the server 430 to produce intermediate format data 445, transmitting the intermediate format data 445 to an application 450, and decoding the intermediate format data 445 into computer-readable format data using the application 450 and context information associated with the application 450.

Description

TECHNICAL FIELD The present invention relates to a method of and system for natural language recognition, and in particular, to a method of and system for computer-based recognition of natural language data implemented on a distributed computer network. CO-PENDING APPLICATIONS Various methods, systems and apparatus relating to the present invention are disclosed in the following co-filed U.S. application, the disclosures of which are incorporated herein by cross-reference:NPW012U.S.CROSS REFERENCES Various methods, systems and apparatus relating to the present invention are disclosed in the following granted U.S. patents and co-pending U.S. applications filed by the applicant or assignee of the present application: The disclosures of all of these granted U.S. patents and co-pending U.S. applications are incorporated herein by reference. 10 / 409,87610 / 409,84810 / 409,84509 / 575,19709 / 575,19509 / 575,15909 / 575,13209 / 575,12309 / 575,14809 / 575,13009 / 575,16509 / 575,15309 / 693,41509 / 575,11809 / 6...

AI Technical Summary

Benefits of technology

In another form, the present invention also seeks to provide means for managing multiple recognizers, user-specific dictionaries, and user-specific training of recognizers, desirable to make pattern recognition systems more accurate and flexible.

Problems solved by technology

Natural language input is inconsistent, noisy, and ambiguous, leading to potential recognition and decoding errors.

However, high recognition accuracy is required for pattern recognition applications to operate successfully, since mistakes can be expensive and frustrating to users.

The problem domain for many pattern recognition systems is inherently ambiguous (i.e. many of the input patterns encountered during processing cannot be accurately classified without further information from a different source).

As an example, one of the major issues faced in the development of highly accurate handwriting recognition systems is the inherent ambiguity of handwriting (e.g. the letters ‘u’ and ‘v’, ‘t’ and ‘f’, and ‘g’ and ‘y’ are often written with a very similar appearance and are thus easily confused).

Presently, handwriting recognition accuracy remains relatively low, and the number of errors introduced by recognition (both for the database entries and for the handwritten query) means that present techniques do not work well.

The process of converting handwriting into text results in the loss of a significant amount of information regarding the general shape and dynamic properties of the ink.

Images