Semantic Pruning of Requirement Specifications: An NLP Framework for Redundancy Detection
Bibliographic record
Abstract
Software Requirement Specifications (SRS) often contain redundant, ambiguous, or inconsistent requirements that increase costs and delay project timelines. Traditional redundancy detection methods such as TF-IDF or Word2Vec rely mainly on syntactic similarity and struggle to capture semantic overlaps. This paper proposes a semantic pruning framework using advanced NLP techniques, with a focus on transformer-based models like BERT, to detect and eliminate redundant requirements in SRS documents. A comparative study of approaches including CountVectorizer, TF-IDF, Word2Vec and BERT was conducted using precision, recall, F1-score, and runtime as evaluation metrics. Results show that while traditional methods achieve high precision but low recall, deep learning models perform significantly better. Word2Vec achieved F1 = 0.81, while BERT delivered the best performance with F1 = 0.87 and recall = 0.77, albeit with higher runtime. The findings highlight the effectiveness of transformer-based embeddings for redundancy detection and provide a scalable solution for improving SRS quality and reducing manual review effort.
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 | 0.003 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".