Inicio  /  Applied Sciences  /  Vol: 13 Par: 7 (2023)  /  Artículo
ARTÍCULO
TITULO

An Abstractive Summarization Model Based on Joint-Attention Mechanism and a Priori Knowledge

Yuanyuan Li    
Yuan Huang    
Weijian Huang    
Junhao Yu and Zheng Huang    

Resumen

An abstractive summarization model based on the joint-attention mechanism and a priori knowledge is proposed to address the problems of the inadequate semantic understanding of text and summaries that do not conform to human language habits in abstractive summary models. Word vectors that are most relevant to the original text should be selected first. Second, the original text is represented in two dimensions?word-level and sentence-level, as word vectors and sentence vectors, respectively. After this processing, there will be not only a relationship between word-level vectors but also a relationship between sentence-level vectors, and the decoder discriminates between word-level and sentence-level vectors based on their relationship with the hidden state of the decoder. Then, the pointer generation network is improved using a priori knowledge. Finally, reinforcement learning is used to improve the quality of the generated summaries. Experiments on two classical datasets, CNN/DailyMail and DUC 2004, show that the model has good performance and effectively improves the quality of generated summaries.

 Artículos similares

       
 
Qicai Wang, Peiyu Liu, Zhenfang Zhu, Hongxia Yin, Qiuyue Zhang and Lindong Zhang    
As a core task of natural language processing and information retrieval, automatic text summarization is widely applied in many fields. There are two existing methods for text summarization task at present: abstractive and extractive. On this basis we pr... ver más
Revista: Applied Sciences

 
Xiujuan Xiang, Guangluan Xu, Xingyu Fu, Yang Wei, Li Jin and Lei Wang    
Current popular abstractive summarization is based on an attentional encoder-decoder framework. Based on the architecture, the decoder generates a summary according to the full text that often results in the decoder being interfered by some irrelevant in... ver más
Revista: Information

 
Afrida Helen     Pág. 22 - 34
Understanding the contents of numerous documents requires strenuous effort. While manually reading the summary or abstract is one way, automatic summarization offers more efficient way in doing so. The current research in automatic summarization focuses ... ver más