Automatic Documents Analyzer and Classifier
Bibliographic record
Abstract
Military organizations have to deal with an increasing number of documents coming from different sources and in various formats (paper, fax, e-mail messages, electronic documents). These documents have to be screened, analyzed and categorized in order to interpret their content and gain situation awareness. These documents should be categorized according to their content to enable efficient storage and retrieval. In this context, intelligent techniques and tools should be provided to support this information management process that is currently partly manual. Integrating the recently acquired knowledge in different fields in a system for analyzing, diagnosing, filtering, classifying and clustering documents with a limited human intervention would improve efficiently the quality of information management with reduced human resources. A better categorization and management of information would facilitate correlation of information from different sources, avoid information redundancy, improve access to relevant information, and thus better support decision-making processes. The RDDC-Valcartier's ADAC system (Automatic Documents Analyzer and Classifier) incorporates several techniques and tools for document summarizing and semantic analysis based on ontology of a certain domain (e.g. terrorism), and algorithms of diagnostic, classification and clustering. In this paper, we describe the architecture of the system and the techniques and tools used at each step of the document processing. For the first prototype implementation, the focus has been concentrated on the terrorism domain to develop document corpus and related ontology.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.010 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.015 | 0.016 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".