Global Encoding for Abstractive Summarization

ACL 2018  ·  Junyang Lin, Xu sun, Shuming Ma, Qi Su ·

In neural abstractive summarization, the conventional sequence-to-sequence (seq2seq) model often suffers from repetition and semantic irrelevance. To tackle the problem, we propose a global encoding framework, which controls the information flow from the encoder to the decoder based on the global information of the source context. It consists of a convolutional gated unit to perform global encoding to improve the representations of the source-side information. Evaluations on the LCSTS and the English Gigaword both demonstrate that our model outperforms the baseline models, and the analysis shows that our model is capable of reducing repetition.

PDF Abstract ACL 2018 PDF ACL 2018 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Summarization GigaWord CGU ROUGE-1 36.3 # 29
ROUGE-2 18.0 # 24
ROUGE-L 33.8 # 29

Methods


No methods listed for this paper. Add relevant methods here