python 3
This project extracts concepts with different mechanisms
TFIDF
TFIDFNP
LDA
wikipedia titles as concepts
wikipedia sections as concepts
ACM publication Keywords as concepts
Global Ngrams
Also it has possiblity to learn representation for these concepts using
Concept2Vec
Doc2Vec
Word2Vec
For using concept_extractor
- You have to have a text file with text in : IR_CORPUS = 'add the path to your file here'
- And uncomment the concept method you want to run
- The concepts will be generated in folder keyphrase_output
Failure of Marisa Trie ... point explicity to C path
export MACOSX_DEPLOYMENT_TARGET=10.9 export CPATH=/Library/Developer/CommandLineTools/usr/include/c++/v1