Model Finetuning for NLI

This lecture covers the second assignment for the CS-552: Modern NLP course, focusing on transfer learning and data augmentation. Students will implement training and evaluation of a pre-trained language model (DistilBERT) for natural language inference (NLI) tasks. They will identify model shortcuts, perform word-pair pattern extraction, annotate new data, and explore data augmentation methods. The lecture provides detailed instructions and code snippets for each part of the assignment, including model finetuning, identifying model shortcuts, and data augmentation.