[BangPypers] NLTK

[Gopalakrishnan Subramani]

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