A Hybrid Text Summarization Approach Using Neural Networks and Metaheuristic Algorithms
Bibliographic record
Abstract
The rapid growth of text data on the Internet requires effective automatic text summarization techniques.This study proposes a hybrid text summarization approach that combines a Multi-hidden Recurrent Neural Network and a mayfly-harmony search algorithm.The neural network generates a feature vector for each sentence.The mayflyharmony search algorithm then optimizes the feature weights to extract the most relevant sentences for the summary.This manuscript capacity provides essential information and expertise that can be effectively summarised using Efficient Abstractive Text Summarising (EATS) techniques.This project aimed to extract informative summaries from various articles by utilizing regularly utilized handcrafted elements from literature.A Multi-hidden Recurrent Neural Network (MRNN) was used to generate a feature vector, and a new feature assortment strategy called Mayfly-Harmony Search (MHS) was applied for feature extraction.The number of sentences, word frequency, title similarity, term frequency-inverse sentence frequency, sentence location, sentence length, sentencesentence similarity, sentence phrases, proper nouns, n-gram co-occurrence, and document length were the features used.By taking diverse Mayfly Algorithm explanations found from other expanses of the search space and processing them with Harmony Search, the suggested hybrid of the Mayfly Algorithm and Harmony Search was employed to produce superior results.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| 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) | 0.002 | 0.000 |
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".