Publications & Patents
See also Google Scholar for citations. Papers marked Under review link to preprints.
LLMs & Recommendation Comcast Applied AI Research, 2024–present
UNDER REVIEW
From Head to Tail: LLM-Augmented Sequential Recommendation and Trade-off Optimization
LLM-Driven Segment Discovery: Uncovering Latent User Intent at Scale
Candidate Grounding Matters: LLM-Guided Negative Selection for Production Recommenders
2026
From Head to Tail: LLM-Augmented Sequential Recommendation and Trade-off Optimization
Evaluating ASR Quality at Scale on TV Entertainment Platforms
2025
Simulating Discoverability for Upcoming Content on Entertainment Platforms
Content Moderation in TV Search: Balancing Compliance, Relevance, and User Experience
Earlier work: NLP for Low-Resource Dravidian Languages With Prof. Bharathi Raja Chakravarthi, Sep 2020 – Jan 2022
2025
Do Images Really Do the Talking? Analyzing the Significance of Images in Tamil Troll Meme Classification
2022
Multi-task Learning in Under-resourced Dravidian Languages
How Can We Detect Homophobia and Transphobia? Experiments in a Multilingual Code-Mixed Setting for Social Media Governance
The Best of Both Worlds: Dual Channel Language Modeling for Hope Speech Detection in Low-resourced Kannada
DE-ABUSE@TamilNLP-ACL 2022: Transliteration as Data Augmentation for Abuse Detection in Tamil
Findings of the Shared Task on Multi-task Learning in Dravidian Languages
Findings of the Second Shared Task on Troll Meme Classification in Tamil
Findings of the Shared Task on Emotion Analysis in Tamil
2021
Domain Identification of Scientific Articles Using Transfer Learning and Ensembles
Evaluating Pretrained Transformer-based Models for COVID-19 Fake News Detection
Offensive Language Identification in Low-resourced Code-mixed Dravidian Languages Using Pseudo-labeling
IIITT@LT-EDI-EACL2021 – Hope Speech Detection: There Is Always Hope in Transformers
UVCE-IIITT@DravidianLangTech-EACL2021: Tamil Troll Meme Classification: You Need to Pay More Attention
IIITT@DravidianLangTech-EACL2021: Transfer Learning for Offensive Language Detection in Dravidian Languages
IIITT at CASE 2021 Task 1: Leveraging Pretrained Language Models for Multilingual Protest Detection
Attentive Fine-tuning of Transformers for Translation of Low-resourced Languages @LoResMT 2021
Hypers at ComMA@ICON: Modelling Aggressive, Gender Bias and Communal Bias Identification
Findings of the Sentiment Analysis of Dravidian Languages in Code-Mixed Text
2020
KanCMD: Kannada CodeMixed Dataset for Sentiment Analysis and Offensive Language Detection
Patents
Systems for content filtering
Systems for enhancing content discoverability in TV systems