International Business Machines Corporation

Albert T Wong

Craig M Trim

Ahmed M Nassar

Stephen J Edwards

Tushar Agrawal

Reinaldo T Katahira

Sarbajit Kumar Rakshit

Barton Wayne Emanuel

Ahmed M A Nassar

Marcy L Wagman

Asieh Dicken

Margaret A Strong

Embodiments described herein provide approaches for validating synonyms in ontology driven natural language processing. Specifically, an approach is provided for receiving a user input containing a token, structuring the user input into a semantic model comprising a set of classes each containing a set of related permutations of the token, designating the token as a synonym of one of the set of related permutations, annotating the token with a class from the set of classes corresponding to the one of the set of related permutations, and validating the annotation of the token by determining an accuracy of the designation of the token as a synonym of the one of the set of related permutations. In one embodiment, the accuracy is determined by quantifying a linear distance between the token and a contextual token also within the user input, and comparing the linear distance to a pre-specified linear distance limit.

Contextual validation of synonyms in otology driven natural language processing

A system, method and computer program product to validate documents is provided. A processor receives an image of a document. The processor identifies a plurality of fixed contents of the document. The processor identifies a plurality of field contents of the document. The processor determines a type of the document based, at least in part, on the plurality of fixed contents and the plurality of field contents. The processor validates the plurality of field contents of the document based, at least in part, on rules associated with the type of the document. The processor generates a validated document.

Field verification of documents

To recombine incorrectly separated tokens in NLP, a determination is made whether a token from an ordered set of tokens is present in a dictionary related to a corpus from which the ordered set is extracted. When the token is not present in the dictionary, and when a compounding threshold has not been reached, the token is agglutinated with a next adjacent token in the ordered set to form the compound token. The compounding threshold limits a number of tokens that can be agglutinated to form a compound token. A determination is made whether the compound token is present in the dictionary. A weight is assigned to the compound token when the compound token is present in the dictionary and a confidence rating of the compound token is computed as a function of the weight. The compound token and the confidence rating are used in NLP of the corpus.

Recombining incorrectly separated tokens in natural language processing

Disclosed are a learning system and method for auditory learners. The system comprises recording means for capturing, digitizing, storing, and indexing voice statements; and means for allowing an auditory learner to search said indexing for desirable voice statements. The learning system further comprises means for playing on demand and broadcasting said desired voice statements to said auditory learner; means for creating an auditory live session for said learner; and means for mining said voice statements for emerging subject matter and to create new voice statements for playing on demand to said learner. The preferred embodiment of the invention is a new deployment vehicle for informal learning cultivated within a Community of Practice and broadcast over IP.

Multiplatform voice over IP learning deployment methodology

Growing community of inventors

Hacienda Heights, CA, United States of America

Albert T Wong