Transformer-Based Text Highlighting for Medical Terms
Bibliographic record
Abstract
This paper makes use of transformer models for text highlighting in medical documents aiming the medical professionals to efficiently pinpoint the information they need by focusing on important keywords in the texts. Medical text datasets such as the PHEE dataset, which includes over 5,000 annotated events from case reports, and the MTSamples dataset are utilized to train and test models for word-level text highlighting. Importantly, a large number of data instances from these datasets are carefully annotated, which can help future research in this field. Three different methodologies are implemented: BERT fine-tuning, BERT-CRF, and Automatic Concatenation of Embeddings (ACE). For each methodology, five model checkpoints are compared. Additionally, different fine-tuning strategies, including adaptive fine-tuning, are applied to enhance the results across different datasets. Our comparative analysis shows that DeBERTa and BERT-Clinical models are highly effective in capturing key information from complex medical texts. Furthermore, by utilizing the trained models, we introduce a color-coded text highlighting procedure that can help facilitate capturing the important information in the medical 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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.004 |
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".