Hitesh Golchha

I am currently pursuing MS in CS from UMass Amherst. I am actively looking for Internship roles for Summer 2022. My current courses include Reinforcement Learning(687), Machine Learning(689), and Neural Networks: A Modern Introduction (682)

For two years at Flipkart (Walmart), I worked on problems in Conversational AI: intent detection, entity extraction, sentence segmentation and rescoring ASR beams. Challenges included handling multilinguality, class imbalance, miscalibration, augmentation and robustness. The voice assistants we developed are used by millions of Indians for E-commerce shopping every day. I also participated in hackathons on unsupervised reverse image search and question answering.

I did my B.Tech. in Computer Science and Engineering from Indian Institute of Technology (IIT) Patna, India. I was guided by Dr. Asif Ekbal and Prof. Pushpak Bhattacharyya for my B.Tech Thesis and during my Junior Research Fellowship. I also did a short research internship at Bar Ilan University under Prof. Ido Dagan after my Junior Year.

My research endeavours have been on Style transfer for dialog response generation, Natural Language Understanding for agents, Suggestion Mining, Coreference Resolution, and Question answering.

June update: I started my YouTube channel, "The Random Variable". I intend to discuss ideas, papers, math and code. Latest video: "Reformer explained (Paper + šŸ¤—Hugging Face code)"

Email  /  CV  /  Google Scholar  /  Twitter  /  Github  /  YouTube  / 

profile photo
Research

My research has focused on solving several semantic tasks in Natural Langauge Processing using Machine Learning algorithms.

clean-usnob Courteously Yours: Inducing courteous behavior in Customer Care responses using Reinforced Pointer Generator Network
Hitesh Golchha*, Mauajama Firdaus*, Asif Ekbal, Pushpak Bhattacharyya
NAACL-HLT ,2019

We develop a system that transforms a generic customer care response into a 'Courteous' one. The model takes into context the emotions and content of the conversation history as well while generating and is trained on MLE+RL.

bibtex
clean-usnob A Deep Multi-task Model for Dialogue Act Classification, Intent Detection and Slot Filling
Mauajama Firdaus, Hitesh Golchha, Asif Ekbal, Pushpak Bhattacharyya
Cognitive Computation ,2020

We compare multi-task approaches with standalone and pipeline ones for Spoken Language Understanding tasks on ATIS, TRAINS and FRAMES datasets.

bibtex
clean-usnob Helping each Other: A Framework for Customer-to-Customer Suggestion Mining using a Semi-supervised Deep Neural Network
Hitesh Golchha, Deepak Gupta, Asif Ekbal, Pushpak Bhattacharyya
International Conference on Natural Language Processing (ICON),2018

We develop a linguistically informed, self-supervised model to identify customer-to-customer suggestions in Hotel and Electronics review datasets.

bibtex
Timeline
clean-usnob UMass Amherst
MS CS, Fall 2021 - now

Courses: Reinforcement Learning(687), Machine Learning(689), and Neural Networks: A Modern Introduction (682)

clean-usnob Flipkart
Software Development Engineer (Data Science), April 2019 - April 2021

Multiple research tasks in the NLU: Intent detection, slot filling, multi-intent sentence segmentation, data augmentation, ASR beam rescoring. Challenges included handling multilinguality, class imbalance, miscalibration, augmentation and robustness. The voice assistants we developed are used by millions of Indians for E-commerce shopping every day. I also participated in hackathons on unsupervised reverse image search and question answering.

clean-usnob AI-NLP-ML Lab, IIT Patna
Junior Research Fellow, July - Dec 2018

Research in the domain of conversational agents: NLU and Style Transfer in Response Generation.

clean-usnob NLP Lab, Bar Ilan University
Research Internship,May-Jul 2017

Research in Coreference Resolution of Propositions. I got an exposure to several tasks in NLP associated with creation of Natural Language Knowledge Graphs.

clean-usnob AI-NLP-ML Lab, IIT Patna
Undergradute Researcher, May 2016 - May 2018

Research in Suggestion Mining, Question Answering

Please checkout Jon Barron's website if you want to use this Layout.