Step 2 [5 points] - Indexing

[dkutin]

Build an inverted index, with an entry for each word in the vocabulary. You can use any appropriate data structure (hash table, linked lists, Access database, etc.). An example of a possible index is presented below.

• Input: Tokens obtained from the preprocessing module
• Output: An inverted index for fast access

For weighting, you can use the tf-idf weighting scheme (w_ij = tf_ij x idf_i). For each query, your system will produce a ranked list of documents, starting with the most similar to the query and ending with the least similar. For the query terms, you can use a modified tf-idf weighting scheme w_iq = (0.5 + 0.5 tf_iq)∙idf_i