Project to examine open text classification using deep learning

Report

open-classification-text_final_report.pdf

Files

• Project Notebook:

  • Implementation Specs and Notes: Text_Open_Classification_Implementation_Spec_and_Notes.ipynb

  • Paragraph2Vec workbook: Text_Open_Classification_Paragraph2vec_workbook.ipynb

  • Paragraph vector GMM (5 seen + 1 unseen classes): ParagraphVec_Clustering_5_plus_1.ipynb

  • Paragraph vector GMM (5 seen + 2 unseen classes): ParagraphVec_Clustering_5_plus_2.ipynb

  • Paragraph vector GMM (5 seen + 3 unseen classes): ParagraphVec_Clustering_5_plus_3.ipynb

  • Paragraph vector IDP (5 seen + 1 unseen classes): ParagraphVec_Clustering_5_plus_1-IDP.ipynb

  • Paragraph vector IDP (5 seen + 2 unseen classes): ParagraphVec_Clustering_5_plus_2-IDP.ipynb

  • Paragraph vector IDP (5 seen + 3 unseen classes): ParagraphVec_Clustering_5_plus_3-IDP.ipynb

  • CNN implementation and training workbook: Text_Open_Classification_CNN_workbook.ipynb

  • CNN Open classification 1-vs-rest, GMM, IDP (5 seen + 1 unseen classes): CNN_open_classification_5_plus_1.ipynb

  • CNN Open classification 1-vs-rest, GMM, IDP (5 seen + 2 unseen classes): CNN_open_classification_5_plus_2.ipynb

  • CNN Open classification 1-vs-rest, GMM, IDP (5 seen + 3 unseen classes): CNN_open_classification_5_plus_3.ipynb

• Data_Set: Contain raw data of 20 newsgroup data set. Formatted data can be accessed directly from Scikit-learn package

Resources

Project Proposal and Plan Document:

• Initial proposal: https://docs.google.com/document/d/1stzkcY4zR5NncOMhOfePjYtgVQawLY9O56kCAPPlfpE/edit

• Project milestone report W266_project_milestone_report.pdf

Reference papers:

DOC: Deep Open Classification of Text Documents

• http://aclweb.org/anthology/D17-1313

Convolutional Neural Networks for Sentence Classification

• http://www.aclweb.org/anthology/D14-1181

A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification

• https://arxiv.org/abs/1510.03820

More Reference Materials

https://www.cs.uic.edu/~liub/lifelong-learning.html

http://blog.echen.me/2012/03/20/infinite-mixture-models-with-nonparametric-bayes-and-the-dirichlet-process/