There are 0 repository under text-cla topic.
Constructed a structured heterogeneous text corpus graph to transform text classification problem into a node classification problem. Created semantic rich features by using Text GCN and topic modeling based approach-LDA which are then fed into a novel classification model.
This repository will provide an overview and working knowledge of Natural Language Processing (NLP), using Python’s Natural Language Toolkit (NLTK) library and with Keras.
Implemented word embedding and transfer learning to classify comments into toxic or non-toxic comments using Convolution. The model was able to classify comments into toxic or non-toxic with accuracy >= 95%.