Pinkesh Badjatiyapinkeshbadjatiya [at] gmail [dot] com | +91-720-774-6433 Resume | Google Scholar | dblp | LinkedIn | Github I am currently working as an Applied Scientist 2 with the Search Technology Center India (STCI) AI Products team at Microsoft (R&D) working on relevance and ranking systems for the PeopleAlsoAsk Experience. I work on large-scale NLP recommendation systems that show relevant questions to Bing users while maximizing user engagement & experience. I work on mining signals from massive interaction data at Bing scale, building large-scale ML models, utilizing Machine Learning to distill information, and deploying them with Web-ready latency (<10ms). Prior to this, I worked with the Media and Data Science Research (MDSR) Lab - a BU embedded research group in Digital Marketing at Adobe as a Machine Learning Researcher and Engineer 2, where I mainly focused on Computer Vision and Reinforcement Learning. I am interested in artificial intelligence, natural language processing, machine learning, and computer vision. Much of my research is in Deep Reinforcement Learning (Deep-RL), Natural Language Processing (NLP), and training Deep Neural Networks to solve complex social problems. I am also interested in bringing these recent developments in AI to production systems. I finished my MS by Research in Machine Learning with a focus in the domain of Information Retrieval and Extraction (IRE) from IIIT Hyderabad under the guidance of Prof. Vasudeva Varma (former Dean R&D, IIIT Hyderabad) and Prof. Manish Gupta (Microsoft, India). My thesis was encompassing the realm of Hate Speech Detection and Bias Mitigation in neural networks. Insights from my research work subsequently resulted in the formation of Project ANGEL which later garnered the Google AI/ML Research Award 2020. Other projects I worked on during my studies include Trust Inference in Social Network, Document Segmentation, Text Summarization and Project Sexism. I also completed my B.Tech with Honours in Computer Science and Engineering from IIIT Hyderabad. I feel fortunate to have worked with some of the amazing folks from both Academia and Machine Learning Research. Just to thank a few folks; Manish Gupta, Georgios Theocharous, Balaji Krishnamurthy, Jayakumar Subramanian, Mausoom Sarkar, Niyati Chhaya, and Vasudeva Verma. I spend most of my time reading books. I also spend my spare time pursuing my childhood passion; following Astronomy, General Relativity, and Quantum Mechanics. Occasionally, I play piano (Youtube), listen to music, eat, drink, and sleep. |
|
Applied Scientist 2October 2021 - CurrentI am primarily working on building innovative NLP and Multi-Modal solutions for BING search using Machine Learning/Deep Learning techniques. |
|
Machine Learning Researcher & Engineer 2June 2019 - October 2021 (2 years, 4 months)I primarily work with Data Science, NLP, and Reinforcement Learning research. I also work towards building ML algorithms for production. |
|
Machine Learning Research InternJan 2019 - April 2019 (4 months)Working towards solving social dilemmas for Multi-agent setting using Deep Reinforcement Learning using Model-based Value functions. Extended a full-time offer. |
|
Computer Vision Engineer◉ Remote ◉ FreelanceDecember 2019 - April 2021
|
|
Software Engineer InternMay 2018 - July 2018 (3 months)Designed an algorithmic solution using constraint optimization in java and scala. Used TDD with OOP concepts and Design patterns. Performed error analysis and deployed to production. Extended a full-time offer. |
|
Data Analytics/Site Reliability Engineer InternSep 2017 - Mar 2018 (7 months)Developed analytics from the reports produced by ~280 co-working startups incubated at T-Hub. Analyzed the user traffic flows to improve the site experience and generate weekly statistics for internal-analysis using Google Analytics and Python |
|
Google Code-In MentorNov 2016 - Jan 2017 (3 months)Mentored students working on the ListenBrainz project. Tasks involved creating tasks of varying difficulty levels and evaluating their submissions. |
|
System Administrator and OrganizerJul 2016 - Jun 2017 (11 months)Felicity Threads is the annual technical fest of IIIT Hyderabad. I was part of the team responsible for maintaing the contest portals and the website for the fest. I was also a problem setter for the event Break-In CTF and |
|
Google Summer Of Code (GSoC) InternApril 2016 - August 2016 (4 months)Created a proxy submission Flask API compatible with Last.fm scrobblers. Added scrobbling support for desktop clients with support for tracking currently playing song in Redis. |
2021 |
|
2021 |
|
2020 |
|
2020 |
|
2020 |
|
2019 |
|
2019 |
|
2018 |
|
2018 |
|
2018 |
|
2017 |
|
2017 |
|
2017 |
|
2016 |
|
2016 |
|
2015 |
|
2014 |
|
2014 |
|
|
Framework for Structured Prompt Building For a Generative Language ModelPinkesh Badjatiya, Rajpal Kulhari, Aditi Gulati, Aditi Agrahari, Kishor Chamua, Thuli Nitoshe Chishi, Harendra Prasad Baji(Submitted) |
|
Optimal sequential decision making with changing action spacePinkesh Badjatiya, Tanay Anand, Jayakumar Subramaniam, Sriyash Poddar, Georgios Theocharous, Balaji Krishnamurthy,(Submitted) |
|
Status-Quo Policy Gradient for Multi-agent Reinforcement LearningPinkesh Badjatiya, Mausoom Sarkar, Jayakumar Subramaniam, Abhishek Sinha Nikaash Puri, Balaji Krishnamurthy,(Submitted) |
|
High Utility Sequential Pattern Mining using Reinforcement LearningTanay Anand, Piyush Gupta, Pinkesh Badjatiya, Nikaash Puri, Jayakumar Subramaniam, Balaji Vasan Srinivasan, Chirag Singla, Rachit Bansal, Anil Singh Parihar(Submitted) |
|
Dynamic Non-Linear Interpolation of Latent Vectors for Semantic Face EditingPinkesh Badjatiya, Parth PatelUS Patent 17/454,645 (Filed) |
|
Semantics-Aware Hybrid Encoder For Improved Related ConversationsPinkesh Badjatiya, Tanay Anand, Simra Shahid, Nikaash Puri, Milan Aggarwal, S Sejal Naidu, Sharat Chandra Racha, Ganesh Palwe, Balaji Krishnamurthy(Submitted) |
|
SHERLock: Self-Supervised Hierarchical Event Representation LearningSumegh Roychowdhury, Sumedh A Sontakke, Nikaash Puri, Mausoom Sarkar, Milan Aggarwal, Pinkesh Badjatiya, Balaji Krishnamurthy, Laurent Itti(Submitted) |
|
TAN-NTM: Topic Attention Networks for Neural Topic ModelingShashank Shailabh, Madhur Panwar, Milan Aggarwal, Pinkesh Badjatiya, Simra Shahid, Nikaash Puri, Sejal Naidu, Sharat Chandra, Balaji Krishnamurthy, Ganesh Palwe(Submitted) |
|
Entropy Based Synthetic Data Generation For Augmenting Classification System Training DataPinkesh Badjatiya, Nikaash Puri, Ayush Chopra, Anubha KabraUS Patent 16/659,147 (Published) |
|
Text Conditioned Image Search Based On Dual-disentangled Feature CompositionPinkesh Badjatiya, Surgan Jandial, Pranit Chawla, Mausoom Sarkar, Ayush ChopraUS Patent 17/160,862 (Filed) |
|
Text-conditioned Image Search Based On Transformation, Aggregation, And Composition Of Visio-linguistic FeaturesPinkesh Badjatiya, Surgan Jandial, Pranit Chawla, Mausoom Sarkar, Ayush ChopraUS Patent 17/160,893 (Filed) |
I'm interested in computer vision, machine learning and its applications, and natural language processing (NLP). Representative papers are highlighted.
|
Understanding Bias in Hate SpeechPinkesh BadjatiyaTutorial Talk @ |
|
Status-Quo Policy Gradient in Multi-agent Reinforcement LearningPinkesh Badjatiya, Mausoom Sarkar, Nikaash Puri, Jayakumar Subramanian, Abhishek Sinha, Siddharth Singh, Balaji KrishnamurthyPublished at |
|
Combating Online Hate Speech Roles of Content, Networks, Psychology, User Behavior and OthersSarah Masud, Pinkesh Badjatiya, Dr. Amitava Das, Dr. Manish Gupta, Dr. Vasudeva Varma, Dr. Tanmoy ChakrabortyTutorial Presented at |
|
Inducing Cooperative behaviour in Sequential-Social dilemmas through Multi-Agent Reinforcement Learning using Status-Quo LossPinkesh Badjatiya, Mausoom Sarkar, Nikaash Puri, Jayakumar Subramanian, Abhishek Sinha, Siddharth Singh, Balaji KrishnamurthyAccepted as |
|
SHERLock: Self-Supervised Hierarchical Event Representation LearningSumegh Roychowdhury, Sumedh A Sontakke, Mausoom Sarkar, Pinkesh Badjatiya, Milan Aggarwal, Nikaash Puri, Balaji Krishnamurthy, Laurent IttiPublished at |
|
SAC: Semantic Attention Composition for Text-Conditioned Image RetrievalSurgan Jandial*, Pinkesh Badjatiya*, Pranit Chawla*, Ayush Chopra*, Mausoom Sarkar, Balaji Krishnamurthy* denotes equal contribution Accepted at |
|
Leveraging Style and Content features for Text Conditioned Image RetrievalPranit Chawla, Surgan Jandial, Pinkesh Badjatiya, Ayush Chopra, Mausoom Sarkar, Balaji KrishnamurthyAccepted at |
|
MixBoost: Synthetic Oversampling with Boosted Mixup for Handling Extreme ImbalanceAnubha Kabra, Ayush Chopra, Nikaash Puri, Pinkesh Badjatiya, Sukriti Verma, Piyush Gupta, Balaji KrishnamurthyPublished at |
|
Towards Identification, Classification and Analysis of Hate Speech on Social MediaPinkesh BadjatiyaIIIT Hyderabad, |
|
Multi-label Categorization of Accounts of Sexism using a Neural FrameworkPulkit Parikh, Harika Abburi, Pinkesh Badjatiya, Radhika Krishnan, Niyati Chhaya, Manish Gupta, Vasudeva VarmaPublished at |
|
Stereotypical bias removal for hate speech detection task using knowledge-based generalizationsPinkesh Badjatiya, Manish Gupta, Vasudeva VarmaPublished at |
|
Attention-based neural text segmentationPinkesh Badjatiya, Litton J Kurisinkel, Manish Gupta, Vasudeva VarmaPublished at |
|
Deep learning for hate speech detection in tweetsPinkesh Badjatiya*, Shashank Gupta*, Manish Gupta, Vasudeva Varma* denotes equal contribution Published at |
|
|||||
Graduate Teaching Assistant
|
Website template borrowed from here.
|