Abstract Text Summarization with a Convolutional Seq2seq Model
By Yong Zhang, Dan Li, Yuheng Wang, Yang Fang, Weidong Xiao. 2019
60 citations recorded by the source corpus.
Abstract text summarization aims to offer a highly condensed and valuable information that expresses the main ideas of the text. Most previous researches focus on extractive models. In this work, we put forward a new generative model based on convolutional seq2seq architecture. A hierarchical CNN framework is much more efficient than the conventional RNN seq2seq models. We also equip our model with a copying mechanism to deal with the rare or unseen words. Additionally, we incorporate a hierarchical attention mechanism to model the keywords and key sentences simultaneously. Finally we verify our model on two real-life datasets, GigaWord and DUC corpus. The experiment results verify the effectiveness of our model as it outperforms state-of-the-art alternatives consistently and statistical significantly.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jeff Wu
- Sergey Levine
- Mohit Bansal
- Jianfeng Gao
- Luke S. Zettlemoyer
- Percy Liang
- Yejin Choi
- Paul Christiano
In Natural Language Processing
- Jeff Wu
- Nisan Stiennon
- Paul Christiano
- Daniel M. Ziegler
- Ryan J. Lowe
- Dario Amodei
- Long Ouyang
- Alec Radford
Citations in the corpus
- Learning to summarize from human feedback (2020, methodology): “7B model on the CNN/DM dataset, and find that we achieve slightly better ROUGE scores than SOTA models [71] from mid-2019 (see Appendix G.”