no code implementations • ICON 2021 • Jash Mehta, Deep Gandhi, Naitik Rathod, Sudhir Bagul
Our work tries to steer the research of sentiment analysis for resource-constrained languages in the direction of Federated Learning.
no code implementations • 25 Jun 2020 • Fenil Doshi, Jimit Gandhi, Deep Gosalia, Sudhir Bagul
We propose two unique masking strategies that try to replace the unnormalized words in the text with their root form using a unique score based on phonetic and string similarity metrics. We use human-centric evaluations where volunteers were asked to rank the normalized text.
no code implementations • 24 Jan 2019 • Himanshu Vaghela, Manan Oza, Sudhir Bagul
Our results show that matched keypoints are more efficient than FREAK descriptor and requires low computation time than various descriptors like SIFT, BRISK and SURF.
no code implementations • 24 Jan 2019 • Manan Oza, Himanshu Vaghela, Sudhir Bagul
The advantage of using such an approach is that the image-to-image translation is semi-supervised, independant of image segmentation and inherits the properties of generative adversarial networks tending to produce realistic.
1 code implementation • 25 Nov 2017 • Aditya Thakker, Suhail Barot, Sudhir Bagul
We present methods for retrieving all the possible expansions of an acronym from Wikipedia and AcronymsFinder. com.