Bibliographic record
Abstract
This paper addresses the task of using natural language generation (NLG) techniques to generate sentences with formal and with informal style. We studied the main characteristics of each style, which helped us to choose parameters that can produce sentences in one of the two styles. We collected some ready-made parallel list of formal and informal words and phrases, from different sources. In addition, we added two more parallel lists: one that contains most of the contractions in English (short forms) and their full forms, and another one that consists in some common abbreviations and their full forms. These parallel lists might help to generate sentences in the preferred style, by changing words or expressions for that style. Our NLG system is built on top of the SimpleNLG package (Gatt and Reiter, 2009). We used templates from which we generated valid English texts with formal or informal style. In order to evaluate the quality of the generated sentences and their level of formality, we used human judges. The evaluation results show that our system can generate formal and informal style successfully, with high accuracy. The main contribution of our work consists in designing a set of parameters that led to good results for the task of generating texts with different formality levels. 1
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 | 0.004 | 0.027 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 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".