Text-Mining

Topic modelling and Text summarization project for the Text mining and search exam, Data Science Msc @ University of Milan Bicocca

NIPS Papers: Topic Modelling and Text Summarization

Authors:

Gaetano Chiriaco

Riccardo Porcedda

Gianmarco Russo

MSc Data Science

How to navigate the repo

WARNING:The original work was conducted in a different folder. Before executing the notebooks, please, modify all paths in the import.

• Papers_Preproc.ipynb: contains all papers preprocessing and feature engineering described in the report

• LDA.ipynb: Topic modeling with Latent Dirichlet Allocation

• PLSA.ipynb: Topic modeling with probabilistic Latent Semantic Analysis

• DocSignal.ipynb: Our 1D U-net Text Summarizer as described in the report

• Sumy.ipynb: Text Summarization with Sumy TextRank for comparison