Dear All, I want to build a simple automatic text based chat bot for mobile, tablet specs for proof of concept.
Some Ref to talk now: http://www.gsmarena.com/samsung_i9300_galaxy_s_iii-4238.php User: Galaxy SIII Weight Chat Bot: 133 g --------- User: Galaxy S<SPACE>III Weight (space between Galaxy S & III) Chat Bot: 133 g ---------------- User: Samsung Galaxy S3 Weight Chat Bot: 133 g ----------------- User: Galaxy S3 Dimensions Chat Bot: 136.6 x 70.6 x 8.6 mm Now I have about 2000+ specs from different companies, plus nutrition data from USDA, each spec has unique id, stored in Mongo DB. some example. [ { Title: "Galaxy SIII", Vendor: "Samsung", _id: ObjectId(...), weight: 133, ... }, { Title: "iPhone 5", Vendor: "Apple", _id: ObjectId(...), weight: 133, ... }, ..... { Title: "Lentils, Cooked, Boiled", Vendor: "Nutrition", protein: 22, ...}, ......... ] The question is, when the user talks about "Samsung Galaxy S3 Weight", "Galaxy SIII Weight", can NLTK predict a product (ex: Galaxy SIII) and give me the unique _id of the product for further look up for group/attribute like weight? Will NLTK right fit for this problem? I am zero to NLTK, any advise would help me. Any other pointer/Python lib might be helpful. -- Krish _______________________________________________ BangPypers mailing list BangPypers@python.org https://mail.python.org/mailman/listinfo/bangpypers
