A Chinese-Vietnamese news document summarization method based on feature association attention mechanism
A technology of document summarization and attention, applied in neural learning methods, computer components, biological neural network models, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] Embodiment 1: as Figure 1-2 As shown, a Chinese-Vietnamese news document summary generation method based on the feature association attention mechanism, the specific steps of the method are as follows:
[0037] a1. Collection of Chinese-Vietnamese bilingual news documents: A data set of 20,000 documents was constructed with the method of manual inspection and machine labeling, of which 12,000 are Chinese news and 8,000 are Vietnamese news, involving issues of common concern between China and Vietnam in recent years Hot news, including policy topics such as the Belt and Road Initiative, also covers tourism, studying abroad, etc. Each news set contains at least two documents, one in Chinese and one in Vietnamese. For each set of events, the selection of reference abstracts selects 4 sentences for each language as the standard.
[0038] a2. Preprocessing of Chinese-Vietnamese bilingual news documents: including steps such as document segmentation, word segmentation, and...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


