Back to Search
Start Over
Text Summarization Method Based on Double Attention Pointer Network
- Source :
- IEEE Access, Vol 8, Pp 11279-11288 (2020)
- Publication Year :
- 2020
- Publisher :
- IEEE, 2020.
-
Abstract
- A good document summary should summarize the core content of the text. Research on automatic text summarization attempts to solve this problem. The encoder-decoder model is widely used in text summarization research. Soft attention is used to obtain the required contextual semantic information during decoding. However, due to the lack of access to the key features, the generated summary deviates from the core content. In this paper, we proposed an encoder-decoder model based on a double attention pointer network (DAPT). In DAPT, the self-attention mechanism collects key information from the encoder, the soft attention and the pointer network generate more coherent core content, and the fusion of both generates accurate and coherent summaries. In addition, the improved coverage mechanism is used to address the repetition problem and improve the quality of the generated summaries. Simultaneously, scheduled sampling and reinforcement learning (RL) are combined to generate new training methods to optimize the model. Experiments on the CNN/Daily Mail dataset and the LCSTS dataset show that our model performs as well as many state-of-the-art models. The experimental analysis shows that our model achieves higher summarization performance and reduces the occurrence of repetition.
- Subjects :
- 0209 industrial biotechnology
General Computer Science
Computer science
pointer network
General Engineering
Attention mechanism
text summarization
02 engineering and technology
computer.software_genre
neural networks
Automatic summarization
020901 industrial engineering & automation
Pointer (computer programming)
0202 electrical engineering, electronic engineering, information engineering
Reinforcement learning
020201 artificial intelligence & image processing
General Materials Science
Data mining
lcsh:Electrical engineering. Electronics. Nuclear engineering
computer
Encoder
lcsh:TK1-9971
Decoding methods
Subjects
Details
- Language :
- English
- ISSN :
- 21693536
- Volume :
- 8
- Database :
- OpenAIRE
- Journal :
- IEEE Access
- Accession number :
- edsair.doi.dedup.....2a78882912296fabaa8e2fc36d4b4832