Research on NLP Based Automatic Summarization Generation Method for Medical Texts
Bibliographic record
Abstract
The fundamental concept underpinning text summarization technology revolves around the capacity to encapsulate the original information into a succinct form, thus equipping individuals to promptly extract essential content from vast data repositories and liberating users from the cumbersome task of processing extensive textual material. In recent years, the exponential proliferation of data in biomedical literature, patient case records, and healthcare documentation, has presented a pressing challenge. This research undertakes the integration of Natural Language Processing (NLP)-related technologies into the domain of medical text summarization. It puts forth a novel solution for generative automatic summarization, with a specific focus on enhancing the model's proficiency in assimilating the semantic nuances inherent in biomedical texts. The methodology incorporates within existing text summarization frameworks to optimize the model's efficacy in handling biomedical data. The empirical findings presented in this study attest to the remarkable precision of the sentence similarity calculation method introduced herein. In a comparative analysis against four alternative methodologies, this approach achieves a high accuracy rate of 90.6%. This outcome highlights the superior predictive performance of the sentence integration similarity calculation method proposed in this research.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 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) | 0.003 | 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".