A Sketch of a Deep Learning Approach for Discovering UML Class Diagrams from System’s Textual Specification
Bibliographic record
Abstract
Drafting a formal or semi-formal model describing the functional requirements of a system from a textual specification is a prerequisite in the context of a model-driven engineering approach, such as the model-driven architecture initiative proposed by OMG. This model, called a platform-independent model (PIM), is used to derive automatically or semi-automatically the source code of a system. Different knowledge-based approaches have been proposed to extract a PIM from a textual specification automatically. These approaches use a predefined set of rules to perform this discovery. These approaches impose several restrictions on the way a specification is written. The emergence of machine learning techniques and more specifically of deep learning and their obvious success among others in several tasks in automatic language processing, such as speech recognition and translation, suggests the possibility of using these techniques to reach our objective. In this paper, we review state of the art in the domain and we sketch a rough deep learning approach to achieve our objective of extracting a PIM from the textual specification of a system.
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.007 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".