Controlled Natural Language for Requirements Specification: A Systematic Literature Review
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Requirements are critical artifacts of the software development life-cycle. They express capabilities that the system should provide, guiding both the development and testing process. Given their significance, requirements specification has attracted the interest of researchers and practitioners in recent years. Requirements specification is an activity where requirements are specified, i.e., documented. In this context, Controlled Natural Languages (CNL) were proposed as a compromise between the ambiguity of natural language and the complexity of formal languages. CNLs enable the specification of requirements using accurate statements that can be processed automatically, while remaining understandable by stakeholders. In this article, we perform a Systematic Literature Review (SLR) to identify, categorize, and compare CNL approaches for requirements specification. The SLR covers 133 primary studies published between 2000 and 2024. We evaluate them according to seven dimensions: context, scope, targeted requirements types, specification technique, tool support, validation method, and adoption. We provide a categorization framework that summarizes the evaluated dimensions, and we identify directions for future research. Our main results reveal: (1) four types of CNL: standalone templates, requirement patterns, elementary templates, and linguistic rules, (2) limited support for automated tools and domain vocabulary usage, and (3) lack of validation through case studies and limited adoption for the majority of approaches.
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.
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 | 0.005 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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) | 0.000 | 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 it