Method and system for improving machine writing quality, computer equipment and storage medium
A quality and machine technology, applied in the field of improving the quality of machine writing, to achieve the effects of flexible and adjustable deletion, improved readability, and avoiding waste
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0069] The invention is a post-step after machine writing, and is used to delete incoherent sentences in the text, so that the output articles are more readable. The input of this module is the article generated by machine writing, and the output is the optimized article.
[0070] The BERT model is a pre-trained model based on the Transformer architecture and has achieved good performance in multiple tasks. In order to better learn the semantic information of the text and the contextual association in the article, the BERT model pre-trains the model through the MLM task and the NSP task; the latter (ie, the NSP task, Next Sentence Prediction) can help us identify the article very well coherence between sentences. The learning object of this task is a series of sentence pairs, half of which are adjacent in the original corpus, that is, the second sentence is the Next Sentence of the first sentence, and the other half are randomly selected non-adjacent sentence pairs. Through ...
Embodiment 2
[0081] Please refer to Figure 4 , Figure 4 It is a structural diagram of a system to improve the quality of machine writing. Such as Figure 4 As shown, the system of the present invention includes:
[0082] BERT model construction module, described BERT model construction module builds coherence reasoner BERT model, and described coherence reasoner BERT model is trained;
[0083] The coherence score triplet acquisition module, the coherence score triplet acquisition module performs sentence processing on the article and then inputs the trained coherence reasoner BERT model to obtain the coherence score, according to the coherence Score builds coherence score triplets;
[0084] A processing module, the processing module constructs a segmentation point list according to the coherence score triplet, and processes the article according to the segmentation point list.
[0085] The BERT model building module collects corpus in relevant designated fields, and trains the BERT ...
Embodiment 3
[0097] combine Figure 1-Figure 3 As shown, this embodiment discloses a specific implementation manner of a computer device. The computer device may comprise a processor 81 and a memory 82 storing computer program instructions.
[0098] Specifically, the processor 81 may include a central processing unit (CPU), or an Application Specific Integrated Circuit (ASIC for short), or may be configured to implement one or more integrated circuits in the embodiments of the present application.
[0099] Among them, the memory 82 may include mass storage for data or instructions. For example without limitation, the memory 82 may include a hard disk drive (Hard Disk Drive, referred to as HDD), a floppy disk drive, a solid state drive (SolidState Drive, referred to as SSD), flash memory, optical disk, magneto-optical disk, magnetic tape or universal serial bus (Universal Serial Bus, referred to as USB) drive or a combination of two or more of the above. Storage 82 may comprise removable...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More