A Federated Approach for Hate Speech Detection
Deep Gandhi*, Jash Mehta*, Jay Gala*, Zeerak Talat
Posts by Collection
portfolio
FedHealth: Blockchain-Based Federated Learning Architecture for Healthcare Data
Jash Mehta*, Deep Gandhi*, Jay Mehta, Rishi Desai, Lynette D’Mello
Automotive Component Failure Prediction
Collaborated with Deloitte to predict tyre life in vehicles using models
FineDeb: A Debiasing Framework for Language Models
Working on debiasing the training of various language models on isolated demographics such as race, gender, etc.
publications
Detection of Spear Phishing using Natural Language Processing
Deep Gandhi, Jash Mehta, and Ramchandra Mangrulkar Published in Chapman and Hall/CRC, 2021.
Music Genre Classification using Transfer Learning on log-based MEL Spectrogram
Jash Mehta, Deep Gandhi, Govind Thakur, and Pratik KananiFederated Learning for Brain Tumor Segmentation on the Cloud
Deep Gandhi, Jash Mehta, Nemil Shah, and Ramchandra Mangrulkar Published in Chapman and Hall/CRC, 2021.
Abstract:
Application of Deep Learning in Cartography Using UNet and Generative Adversarial Network
Deep Gandhi, Govind Thakur, Pranit Bari, Khushali DeulkarIndicFed: A Federated Approach for Sentiment Analysis in Indic Languages
Jash Mehta*, Deep Gandhi*, Naitik Rathod, and Sudhir BagulAblation Analysis of Seq2Seq Models and Vanilla Transformers for Spanish to English Translation
Deep Gandhi*, Jash Mehta*, and Pranit Bari Published in Springer Nature, 2022.
Abstract:
A Federated Approach to Predict Emojis in Hindi Tweets
Deep Gandhi*, Jash Mehta*, Nirali Parekh, Karan Waghela, Lynette D’Mello, and Zeerak TalatA Federated Approach for Hate Speech Detection
Jay Gala*, Deep Gandhi*, Jash Mehta*, Zeerak Talat Published in 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023), 2023.
talks
Deep Probabilistic Programming
Published:
Unicode Machine Learning Summer Course 2021
Published:
Research Seminar for Undergraduates
Published:
teaching
Levyne
Machine Learning Engineer Intern || February, 2020 - May, 2020.
- Built the complete data analysis platform for the marketing team which performed RFM analysis on dynamic data.
- Responsible for building a chatbot using NLTK for customer interaction and a recommendation system using fast.ai.
Unicode Research
Research Student || August, 2020 - Present
Advisor: Swapneel Mehta, Dr. Akash Srivastava
- Working on SimPPL to track online misinformation spread for adaptive governance (currently supported by NYC Media Lab, Wikimedia Foundation, and AI4ABM).
- Leading a project for conducting audience analysis for Yale Daily News to track spread of articles on social media.
- Teaching Assistant: 9-week Machine Learning Course UMLSC 2021, supported by Google Research India with 100+ students.
Dwarkadas J. Sanghvi College of Engineering
Research Assistant || January, 2021 - June, 2021
Advisor: Dr. Ramchandra Mangrulkar
- Made a project dealing with application of Federated Learning for highly sensitive medical data.
- Worked on a research project to identify Spear Phishing using low computational NLP approaches.
- Published 2 first-author chapters for CRC Press in the domains of Federated Learning & NLP
JPMorgan Chase & Co.
Software Engineer Intern || June, 2021 - August, 2021.
- Worked with the Investment Banking team to automate validation checks for every release using Python and pandas.
- Designed a system for automation of evidence store creation for files to be attached to the SNOW ticket reducing the process time from 1.5 hours to 10 mins.
University of Alberta
Graduate Teaching Assistant || September, 2022 - September, 2022.
- Worked as a Teaching Assistant of Basics of Machine Learning (Fall 2022) and Ethics of Data Science (Winter 2023).
- Responsible for conducting office hours, labs, grading assignments and exams, solving student queries, etc.