akshaym96 / information-retrieval-project Goto Github PK
View Code? Open in Web Editor NEWImplemented various tokenizers to tokenize TREC-2014 data which contains 7,50,000 documents on biomedical discipline and used terrier to evaluate precision and recall based on 30 biomedical queries . Reference:- http://sifaka.cs.uiuc.edu/czhai/pub/ir-tok.pdf