E0 334 Assignment 1
In this assignment, we are tasked with implementing a preprocessing and classification pipeline for 3 datasets, namely:
- The Large Movie Review Dataset (IMDB).
- The Stanford Natural Language Inference Corpus (SNLI).
- AG's News Topic Classification Dataset (News).
packages to be imported: nltk=='3.3' scipy='1.1.0' sklearn='0.19.1' pandas=='0.23.4' numpy=='1.15.0'