Unstructured Transportation Safety Board Findings Categorization Using the Knowledge Graph Pipeline
Bibliographic record
Abstract
In this study, the Transportation Safety Board’s (TSB) Findings data was analyzed to assist Transport Canada Civil Aviation (TCCA) in better informing safety policy decision-making. As the TSB Findings data was unstructured, various methods to categorize and analyze unstructured data were explored in the existing literature. It was found that Knowledge Graphs (KGs), in combination with Deep Learning and Natural Language Processing (NLP) models, such as Neuralcoref and REBEL, were versatile and adaptable to different data needs, which could provide insights into the analysis of the TSB data. This paper first emulated and validated the KG pipeline using the BBC News dataset and then applied the KG pipeline technique to the unstructured TSB Findings Reports data consisting of 4,121 rows, each containing text for an incident or accident. The results showed that the model detected an average of 1.03 entities per row of the data and a total of 5,484 relationships or 1.33 relationships per row. Further, the top-four relationships in the graph database structure obtained from Neo4j accounted for 50% of all relations, though not all relations were found to be valuable. However, a few less-frequent relations were also found to be valuable due to their ability to capture critical components of aviation safety. The results of this data pipeline can be used for further analysis and categorization of TSB’s Findings data to improve aviation safety.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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 teacher head, 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".