Assignment#2.txt

#Assignment 2: Create an inverted index from a collection of documents.Till now you work on  three documnets.Now work on 50k.

Create an Inverted Index for the given collection. Make decision for all the trade-offs like data structure for term-index,    posting list. Sorted or not etc. Store the index in the file for later use. Extra points for index compression.

The collection needs to be used is: 50k documents of Hindi in the same way. After that you work on English collection. The collection to be downloaded is: http://users.dsic.upv.es/grupos/nle/clinss.html in Section corpus:The file is "hindi.12.tar.gz.gpg" and the passphrase is "clinss2012fire".

## Note: if you have difficulty in handling gpg file, search on how to decrypt gpg file in your OS.

Hindi Stemmer in Java is here: http://members.unine.ch/jacques.savoy/clef/HindiStemmerLight.java.txt.