I am broadly interested in Natural Language Processing (Speech and Text). I have a special focus on multimodal learning with a goal of advancing representation learning. Currently I am also working on text-to-speech models for low resource indic languages. In the modality of text, I like working on the topics of content moderation and information extraction. I am currently focused on making deep learning models for detecting complex entities in text and help detect implicit hate speech in online conversations.

I am excited to see what multiple modalities together can offer (speech, text and graphs).

Google Scholar

Patents

Apparatuses, methods, and computer program products for generating and selectively outputting abstractive context summaries for multi-party communication channels
U.S. Patent Application No. 17/936,705
Patent-pending

Apparatuses, methods, and computer program products for generating an abstractive context summary scheduling interface configured for scheduling and outputting abstractive context summaries for multi-party communication channels
U.S. Patent Application No. 17/936,695
Patent-pending

Papers

(names in italics indicate main contributor or equal contribution)

M-MELD: A Multilingual Multi-Party Dataset for Emotion Recognition in Conversations
Sreyan Ghosh, S Ramaneswaran, Utkarsh Tyagi, Harshvardhan Srivastava, Samden Lepcha, S Sakshi, Dinesh Manocha
arXiv Code
Under review at Interspeech 2023

CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network
Sreyan Ghosh, Manan Suri, Purva Chiniya, Utkarsh Tyagi, Sonal Kumar, Dinesh Manocha
Link
Under review at IJCAI 2023 Social Track

Context matters! Implicit hate speech classification using a Social and Conversational-Context synergized network
Sreyan Ghosh, Manan Suri, Purva Chiniya, Utkarsh Tyagi, Rajiv Ratn Shah
Accepted at De-factify 2 @ AAAI 2023

Fighting Media Hyper-partisanship With Modern Language Representation Models
Akshi Kumar, Utkarsh Tyagi, Tanish Grover, Utkarsh Tyagi
Link
Published in ICDAM 2021

mFlameGaze: Mobile-Based Flame Gazing for Improving Sustained Attention
Divyashikha Sethia, Anil Singh Parihar, Aheli Ghosh, Tanish Grover, Deep Diwakar, Shivam Kumar, Utkarsh Tyagi
Link Code
Published in COMSNETS 2021

Hybrid Approach of ANN-GWO Technique for Intrusion Detection
Anushka Sharma, Utkarsh Tyagi
Link
Published in RTEICT 2021

Classifying Question Papers with Bloom’s Taxonomy Using Machine Learning Techniques
Minni Jain, Rohit Beniwal, Aheli Ghosh, Tanish Grover, Utkarsh Tyagi
Link
Published in ICACDS 2019