no code implementations • EACL (LTEDI) 2021 • Senthil Kumar B, Aravindan Chandrabose, Bharathi Raja Chakravarthi
Data in general encodes human biases by default; being aware of this is a good start, and the research around how to handle it is ongoing.
no code implementations • LATERAISSE (LREC) 2022 • Senthil Kumar B, Pranav Tiwari, Aman Chandra Kumar, Aravindan Chandrabose
In this paper, we studied the gender bias in monolingual word embeddings of two Indian languages Hindi and Tamil.
1 code implementation • 30 Oct 2022 • Karthik Desingu, Mirunalini P., Aravindan Chandrabose
Specifically, we propose a baseline supervised method on the meta-training set that allows a network to learn highly representative and generalizable feature embeddings for images, that are readily transferable to new few-shot learning tasks.
no code implementations • SEMEVAL 2020 • Kayalvizhi S, Thenmozhi D., Aravindan Chandrabose
For subtask 2, Universal sentence encoder classifier achieves the highest accuracy for development set and Multi-Layer Perceptron applied on vectors vectorized using universal sentence encoder embeddings for the test set.
no code implementations • 13 Mar 2017 • P. Mirunalini, Aravindan Chandrabose, Vignesh Gokul, S. M. Jaisakthi
Our system learns to classify the images based on the model built using the training images given in the challenge and the experimental results were evaluated using validation and test sets.
no code implementations • 13 Mar 2017 • S. M. Jaisakthi, Aravindan Chandrabose, P. Mirunalini
In the preprocessing phase noise are removed using filtering technique and in the segmentation phase skin lesions are segmented based on clustering technique.