Due: 20 May 1999
With the documents parsed, their features extracted, and efficient inverted files of their postings available, you are now in a position to perform the fundamental matching process by which the documents' characterizations are compared to queries against them.
Begin with the kw-inv.d and doclen.d provided in the AIT data directory.
For each keyword, compute the TF-IDF weighting as described in section 3.6 of the FOA text. Once the keywords are weighted, the next task is to use the partial match algorithm found in FOA 3.7 (pg 83) to match queries with documents. For the purpose of this machine problem, you will be using a set of queries found in /public/mp/queries. There should be eight regular (short) queries, and 3 RelFbk (long) ones in the queries file. Use appropriate normalization for each query.
Match each query against the AIT corpus, and return the top 100 results each.
Create a subdirectory match. in your home directory, and place all files named below
<query>...
Please follow this format as faithfully as possible.
To turn these in, you should make a compressed tar file of the directory and then run turnin to submit it for grading, before the due date for the assignment. Assuming you're in your home directory, which should contain your parse directory, the appropriate sequence is:
tar cvf - match | compress > match.tar.Z turnin -c cs133w match.tar.Z
Turning in after the first time overwrites your previously turned-in version.
To make grading easier for the TA, please also print out hardcopies of:
This document was generated using the LaTeX2HTML translator Version 98.1p1 release (March 2nd, 1998)
Copyright © 1993, 1994, 1995, 1996, 1997, Nikos Drakos, Computer Based Learning Unit, University of Leeds.
The command line arguments were:
latex2html mp4-match.tex.
The translation was initiated by Kevin MUNROE on 1999-05-10