Search Results for author:
Found 6 papers, 1 papers with code
IndicFed: A Federated Approach for Sentiment Analysis in Indic Languages
Our work tries to steer the research of sentiment analysis for resource-constrained languages in the direction of Federated Learning.
Normalizing Text using Language Modelling based on Phonetics and String Similarity
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.
MREAK : Morphological Retina Keypoint Descriptor
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.
Semi-Supervised Image-to-Image Translation
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.
Acronym Disambiguation: A Domain Independent Approach
We present methods for retrieving all the possible expansions of an acronym from Wikipedia and AcronymsFinder. com.
