Monthly Report for December 2006

 

 

Project No.: 260671

Funding Agency: Defense Logistics Agency - Defense Technical Information Center

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

 

 

Classification: 

 

Completed the testing work on DTIC documents and the demo is available at: http://128.82.7.147:8080/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

 

None

 

Deviations in Cost/Schedule

 

None

 

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