Chunked N-Grams for Sentence Validation

This paper deals with Sentence Validation - a sub-field of Natural Language Processing. Sentence Validation refers to verification of "Natural Language" sentence on basis of its syntax and semantics. Sentence Validation is usually carried either via Statistical Means (n-grams) or by Semantic Means (by constructing some kind of Knowledge graph). We have tried to integrate the two approaches. Instead of directly using statistical methods, our sentences under-went semantic pre-processing before applying standard Statistical Means. The results for direct Statistical approach is compared with semantically pre-processed statistical approach. (C) 2015 Published by Elsevier B.V.