A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization
arXiv:1805.03616
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.
arXiv commentInternational Joint Conference on Artificial Intelligence and European Conference on Artificial Intelligence (IJCAI-ECAI), 2018
References in corpus (9)
- Sequence to Sequence Learning with Neural Networks
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Convolutional Sequence to Sequence Learning
- A Deep Reinforced Model for Abstractive Summarization
- Language Modeling with Gated Convolutional Networks
- Sequence Level Training with Recurrent Neural Networks
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Selective Encoding for Abstractive Sentence Summarization
- Neural Headline Generation with Sentence-wise Optimization