This paper describes the work done as part of the shared task on Detecting Paraphrases in Indian Languages(DPIL) in Forum for Information Retrieval and Evaluation(FIRE 2016). Paraphrase identification is the task of deciding whether two given text fragments have the same meaning. Our detection system is for Malayalam language and makes use of the cosine similarity measure, an existing state of the art method for determining the similarity between sentences. The experiments were done on the

more »

... ard data set and the results showed that the system was able to give performance comparable to methods employing more sophisticated procedures.