Publications

Transformer based ensemble for emotion detection

Published in WASSA, ACL 2022, 2022

Aditya Kane, Shantanu Patankar, Sahil Khose, Neeraja Kirtane

Detecting emotions in languages is important to accomplish a complete interaction between humans and machines. This paper describes our contribution to the WASSA 2022 shared task which handles this crucial task of emotion detection. We have to identify the following emotions: sadness, surprise, neutral, anger, fear, disgust, joy based on a given essay text. We are using an ensemble of ELECTRA and BERT models to tackle this problem achieving an F1 score of 62.76%. Our codebase (this https URL) and our WandB project (this https URL) is publicly available.

Download here

A Studious Approach to Semi-Supervised Learning

Published in ICBINB, NeurIPS 2021, 2021

Sahil Khose, Shruti Jain, V Manushree

This paper is an ablation study of distillation in a semi-supervised setting, which not just reduces the number of parameters of the model but can achieve this while improving the performance over the baseline supervised model and making it better at generalizing. We find that the fewer the labels, the more this approach benefits from a smaller student network. This brings forward the potential of distillation as an effective solution to enhance performance in semi-supervised computer vision tasks while maintaining deployability.

Download here

XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches

Published in 1. ML for Creativity and Design, 2. Deep Generative Models and Downstream Applications, 3. CtrlGen: Controllable Generative Modeling in Language and Vision, and 4. New in ML workshop, NeurIPS 2021, 2021

Harsh Rathod, Manisimha Varma, Parna Chowdhury, Sameer Saxena, V Manushree, Ankita Ghosh, Sahil Khose

Sketches are a medium to convey a visual scene from an individual’s creative perspective. The addition of color substantially enhances the overall expressivity of a sketch. This paper proposes two methods to mimic human-drawn colored sketches by utilizing the Contour Drawing Dataset. Our first approach renders colored outline sketches by applying image processing techniques aided by k-means color clustering. The second method uses a generative adversarial network to develop a model that can generate colored sketches from previously unobserved images. We assess the results obtained through quantitative and qualitative evaluations.

Download here

Semi-Supervised Classification and Segmentation on High Resolution Aerial Images

Published in Tackling Climate Change with ML, NeurIPS 2021, 2021

Sahil Khose, Abhiraj Tiwari, Ankita Ghosh

This paper proposes a semi-supervised solution to the classification and segmentation task for a high resolution aerial imagery dataset - FloodNet.

Download here

BERT based Transformers lead the way in Extraction of Health Information from Social Media

Published in SMM4H, NAACL 2021, 2021

Sidharth Ramesh, Abhiraj Tiwari, Parthivi Choubey, Saisha Kashyap, Sahil Khose, Kumud Lakara, Nishesh Singh, Ujjwal Verma

This paper describes our submission for the Social Media Mining for Health (SMM4H) 2021 shared tasks. We participated in 2 tasks: (1) Classificiation, extraction and normalization of adverse drug effect (ADE) mentions in English tweets (Task-1) and (2) Classification of COVID-19 tweets containing symptoms (Task-6). We stood first in task 1-a and second in task 1-b and 6.

Download here