Mitesh M. Khapra

IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation Metrics for Indian Languages
A Survey of Adversarial Defences and Robustness in NLP
Scaling Graph Propagation Kernels for Predictive Learning
DailyDialog++ and DEB: A new dataset and new metric to make the evaluation of chatbots and dialogue systems better
Towards Building ASR Systems for the Next Billion Users
Perturbation CheckLists for Evaluating NLG Evaluation Metrics
Unsupervised Deep Video Denoising
A Joint Training Framework for Open-World Knowledge Graph Embeddings
A Systematic Evaluation of Object Detection Networks for Scientific Plots
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
Towards Interpreting BERT for Reading Comprehension Based QA
A Survey of Evaluation Metrics Used for NLG Systems
On the Importance of Local Information in Transformer Based Models
On Incorporating Structural Information to improve Dialogue Response Generation
Towards Transparent and Explainable Attention Models
On Knowledge Distillation From Complex Networks
Efficient Video Classification Using Fewer Frames
Let's Ask Again: Refine Network for Automatic Question Generation
Re-evaluating ADEM: A Deeper Look at Scoring Dialogue Responses
Let's Ask Again: Refine Network for Automatic Question Generation
Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization
Recovering from random pruning: On the plasticity of deep convolutional neural networks