Paraphrase identification of malayalam sentences - an experience

Sentences with different structures may convey the same meaning. Identification of sentences with paraphrases plays an important role in text related research and applications. This work focus on the statistical measures and semantic analysis of Malayalam sentences to detect the paraphrases. The statistical similarity measures between sentences, based on symbolic characteristics and structural information, could measure the similarity between sentences without any prior knowledge but only on the statistical information of sentences. The semantic representation of Universal Networking Language(UNL), represents only the inherent meaning in a sentence without any syntactic details. Thus, comparing the UNL graphs of two sentences can give an insight into how semantically similar the two sentences are. Combination of statistical similarity and semantic similarity score results the overall similarity score. This is the first attempt towards paraphrases of malayalam sentences.