5 papers
It Takes a MAESTRO To Prune Bad Experts
Palaash Goel, Ayush Maheshwari, Tanmoy Chakraborty
Sparsely-activated Mixture-of-Experts (MoE) language models achieve remarkable inference efficiency by activating only a small fraction of parameters per token, yet their full expe…
LexGen: Domain-aware Multilingual Lexicon Generation
Ayush Maheshwari, Atul Kumar Singh, Karthika NJ +3
Lexicon or dictionary generation across domains has the potential for societal impact, as it can potentially enhance information accessibility for a diverse user base while preserv…
ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification
Yashwanth M., Vaibhav Singh, Ayush Maheshwari +2
We propose ARISE, a framework that iteratively induces rules and generates synthetic data for text classification. We combine synthetic data generation and automatic rule induction…
DICTDIS: Dictionary Constrained Disambiguation for Improved NMT
Ayush Maheshwari, Preethi Jyothi, Ganesh Ramakrishnan
Domain-specific neural machine translation (NMT) systems (e.g., in educational applications) are socially significant with the potential to help make information accessible to a di…
FAIR: Filtering of Automatically Induced Rules
Divya Jyoti Bajpai, Ayush Maheshwari, Manjesh Kumar Hanawal +1
The availability of large annotated data can be a critical bottleneck in training machine learning algorithms successfully, especially when applied to diverse domains. Weak supervi…