prakhar21 / Automatic-Glossary-Generation

The projects lets you extract glossary words and their definitions from a given piece of text automatically using NLP techniques

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Unsupervised technique to Glossary and Definition Extraction

Code Files

  1. GPT2-DefinitionModel.ipynb - GPT-2 model for definition generation.
  2. Data_Generator.ipynb - Data Scraper from GoodReads and GradeSaver
  3. Definition_Extraction.ipynb - WordNet model for definition generation.
  4. Glossary_Extraction.ipynb - Chinking strategy pipeline for selection of glossary terms.

For more details of the project and results you can access project presentation here also read my blog

About

The projects lets you extract glossary words and their definitions from a given piece of text automatically using NLP techniques

License:Apache License 2.0


Languages

Language:Jupyter Notebook 100.0%