Shivkaran Singh

Shared Task on Detecting Paraphrases in Indian Languages (DPIL): An Overview

This paper explains the overview of the shared task on “Detecting Paraphrases in Indian Languages” (DPIL) conducted at FIRE 2016. Given a pair of sentences in the same language, participants were asked to detect the semantic equivalence between sentences. This shared task was proposed for four Indian languages, namely Tamil, Malayalam, Hindi, and Punjabi. There were two subtasks given under the shared task on Detecting Paraphrase in Indian Languages. Given a pair of sentences, the subtask-1 was to classify them as paraphrases or not paraphrases. The subtask-2 was to identify whether they are paraphrases or semi-paraphrases or not paraphrases. The dataset created for the shared task has been made available online, and it is the first open-source paraphrase detection corpora for Indian languages. In this overview paper, we describe both subtasks, datasets, evaluation methods and system descriptions as well as performances of the submitted runs.

A Simplified Exposition of Sparsity Inducing Penalty Functions for Denoising

This paper attempts to provide a pedagogical view to the approach of denoising using non-convex regularization developed by Ankit Parekh et al. The present paper proposes a simplified signal denoising approach by explicitly using sub-band matrices of decimated wavelet transform matrix. The objective function involves convex and non-convex terms in which the convexity of the overall function is restrained by parameterized non-convex term. The solution to this convex optimization problem is obtained by employing Majorization-Minimization iterative algorithm. For the experimentation purpose, different wavelet filters such as daubechies, coiflets and reverse biorthogonal were used.