.png){kind=icon}
.png){kind=icon}
Return
Dual Encoding for Abstractive Text Summarization
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2018.2876317.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recurrent neural network-based sequence-to-sequence attentional models have proven effective in abstractive text summarization. In this paper, we model abstractive text summarization using a dual encoding model. Different from the previous works only using a single encoder, the proposed method employs a dual encoder including the primary and the secondary encoders. Specifically, the primary encoder conducts coarse encoding in a regular way, while the secondary encoder models the importance of words and generates more fine encoding based on the input raw text and the previously generated output text summarization. The two level encodings are combined and fed into the decoder to generate more diverse summary that can decrease repetition phenomenon for long sequence generation. The experimental results on two challenging datasets (i.e., CNN/DailyMail and DUC 2004) demonstrate that our dual encoding model performs against existing methods.
Keywords:
Decoding
Encoding
Task analysis
Semantics
Recurrent neural networks
Computational modeling
Abstractive text summarization
dual encoding
primary encoder
recurrent neural network (RNN)
secondary encoder
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
10.5
Papers:
1.1W
Citations:
5.0W