Monthly Report for December 2006
Project No.: 260671
Funding Agency: Defense Logistics Agency -
Award No.: SP4700-05-P-0148
Project Title: Tools for Automatic Extraction of Metadata from DTIC Electronic Documents Collections - Phase II
Project Period: 09/19/05 - 03/14/07
Work Accomplishments during period
Completed the testing work on DTIC documents and the demo is available at: http://184.108.40.206:8080/dtic/validsum166.jsp
We started the classification work for NASA document set. For this we are initially working of building statistics from NASA documents, which can then be used by validation approach for classification.
Metadata Extraction Software Packaging
Package the latest software with validation approach for classification. The workflow for the latest software is shown below.
Figure 1. System Overview
Figure 2. Input Processing
Figure 3. Form Processing
Figure 4. Post Processing
Figure 5. Non Form Processing
Figure 6. Post-Hoc Classification
Problem Areas and Corrective Actions
Deviations in Cost/Schedule
Work to be Accomplished Next Period
1) Continue work on NASA document set.
2) More extensive experimentation with the validation approach for classification
3) Work on validating the extracted metadata