Python library to extend gensim's summarization library
- Replaced gensim's own regex based sentence splitter with Stanford CoreNLP sentence splitter
- Added functions to get sentence number chosen by the summarizer & replace back sentences using the sentence number
- Added summarizer parameter to give user option to ignore placeholders element inside squarebrackets, i.e. [FORMULA], when calculating sentences scores
- Make sure you have Python 3 & setuptools installed
- Install Stanford CoreNLP
- Install with pip
$ pip install gensim_sum_ext
- To use the library, run Stanford CoreNLP
$ java -mx4g -cp "*" edu.stanford.nlp.pipeline.StanfordCoreNLPServer -port 9000 -timeout 50000
- Navigate to example directory
$ cd example
- Install pip requirements
$ pip install -r requirements.txt
- Run the webserver
$ python run.py
- The webpage will be available in 127.0.0.1:5000