Automated Generation of Chinese Text-Image Summaries Using Deep Learning Techniques
Bibliographic record
Abstract
In the era of the internet, an abundance of Chinese text-image content is continuously produced, necessitating effective automated technologies for processing and summarizing these materials.Automated generation of Chinese text-image summaries facilitates rapid comprehension of key information, thereby enhancing the efficiency of information consumption.Due to the unique characteristics of the Chinese language, traditional automatic summarization techniques are inadequately transferable, prompting the development of text-image summary generation technologies tailored to Chinese features.Research indicates that while existing natural language processing and deep learning techniques have made strides in text summarization, deficiencies remain in the deep semantic mining and integration of text-image content.This study primarily focuses on two aspects: Firstly, a generative approach based on an enhanced MaliGAN model, employing deep learning models to improve text generation quality.Secondly, a retrieval-based approach, utilizing cross-modal similarity retrieval to extract text information most relevant to the image content, guiding summary generation.Additionally, this study innovatively proposes a model architecture comprising segmentation, cross-modal retrieval, and adaptive fusion strategy modules, significantly augmenting the accuracy and reliability of text-image summary generation.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".