NLP Project - Sentence Classification - Toxicity- Approx 20,000 comments - ranging from 2 to 30 words. Balanced Data Set. 1. Traditional, pre-2010 NLP and ML techniques used. 2. Dense Word Vectors - w2v & Glove, sentence vector created from averaged word vectors, ANN. 3. Glove combined with bi-LSTMs and 2D Convs.
-
Updated
Dec 25, 2021 - Jupyter Notebook