Pratyush Kumar

IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation Metrics for Indian Languages
Towards Building ASR Systems for the Next Billion Users
Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
Levelling up NLP for Indian Languages
A Systematic Evaluation of Object Detection Networks for Scientific Plots
The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT
IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages
On the weak link between importance and prunability of attention heads
On the Importance of Local Information in Transformer Based Models
PlotQA: Reasoning over Scientific Plots