Assessing Semantic Frames to Support Program Comprehension Activities
Bibliographic record
Abstract
Software developers often rely on natural language text that appears in software engineering artifacts to access critical information as they build and work on software systems. For example, developers access requirements documents to understand what to build, comments in source code to understand design decisions, answers to questions on Q&A sites to understand APIs, and so on. To aid software developers in accessing and using this natural language information, software engineering researchers often use techniques from natural language processing. In this paper, we explore whether frame semantics, a general linguistic approach, which has been used on requirements text, can also help address problems that occur when applying lexicon analysis based techniques to text associated with program comprehension activities. We assess the applicability of generic semantic frame parsing for this purpose, and based on the results, we propose SEFrame to tailor semantic frame parsing for program comprehension uses. We evaluate the correctness and robustness of the approach finding that SEFrame is correct in between 73% and 74% of the cases and that it can parse text from a variety of software artifacts used to support program comprehension. We describe how this approach could be used to enhance existing approaches to identify meaning on intention from software engineering texts.
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 | 0.014 | 0.101 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.010 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.009 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".