Paper Info
Title
A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization.
Abstract
In this paper, we propose a deep learning approach to tackle the automatic summarization tasks by incorporating topic information into the convolutional sequence-to-sequence (ConvS2S) model and using self-critical sequence training (SCST) for optimization. Through jointly attending to topics and word-level alignment, our approach can improve coherence, diversity, and informativeness of generated summaries via a biased probability generation mechanism. On the other hand, reinforcement training, like SCST, directly optimizes the proposed model with respect to the non-differentiable metric ROUGE, which also avoids the exposure bias during inference. We carry out the experimental evaluation with state-of-the-art methods over the Gigaword, DUC-2004, and LCSTS datasets. The empirical results demonstrate the superiority of our proposed method in the abstractive summarization.
Year
DOI
Venue
2018
10.24963/ijcai.2018/619
IJCAI
DocType
Volume
Citations 
Conference
abs/1805.03616
11
PageRank 
References 
Authors
0.52
16
6
Name
Order
Citations
PageRank
Li Wang1386.74
Junlin Yao2110.52
Yunzhe Tao3141.59
Zhong Li4132.24
Wei Liu54041204.19
Qiang Du61692188.27