Generating Sequence Diagram from Natural Language Requirements
Bibliographic record
Abstract
Model-driven requirements engineering is gaining enormous popularity in recent years. Unified Modeling Language (UML) is widely used in the software industry for specifying, visualizing, constructing, and documenting the software systems artifacts. UML models are helpful tools for portraying the structure and behavior of a software system. However, generating UML models like Sequence Diagrams from requirements documents often expressed in unstructured natural language, is time consuming and tedious. In this paper, we present an automated approach towards generating behavioral models as UML sequence diagrams from textual use cases written in natural language. The approach uses different Natural Language Processing (NLP) techniques combined with some rule based decision approaches to identify problem level objects and interactions. Additionally, different quality metrics are defined to assess the validity of generated sequence diagrams in terms of expected behaviour from a given use case. The criteria we established to assess the quality of analysis sequence diagrams can be applied to similar experiments. We evaluate our approach using different case studies concerning correctness and completeness of the generated sequence diagrams using those metrics. In most situations, we attained an average accuracy factor of over 85% and average completeness of over 90%, which is encouraging.
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 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".