DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
Abstract
We propose DeepChannel, a robust, data-efficient, and interpretable neural model for extractive document summarization. Given any document-summary pair, we estimate a salience score, which is modeled using an attention-based deep neural network, to represent the salience degree of the summary for yielding the document. We devise a contrastive training strategy to learn the salience estimation network, and then use the learned salience score as a guide and iteratively extract the most salient sentences from the document as our generated summary. In experiments, our model not only achieves state-of-the-art ROUGE scores on CNN/Daily Mail dataset, but also shows strong robustness in the out-of-domain test on DUC2007 test set. Moreover, our model reaches a ROUGE-1 F-1 score of 39.41 on CNN/Daily Mail test set with merely 1/100 training set, demonstrating a tremendous data efficiency.
Cite
Text
Shi et al. "DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33016999Markdown
[Shi et al. "DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/shi2019aaai-deepchannel/) doi:10.1609/AAAI.V33I01.33016999BibTeX
@inproceedings{shi2019aaai-deepchannel,
title = {{DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization}},
author = {Shi, Jiaxin and Liang, Chen and Hou, Lei and Li, Juanzi and Liu, Zhiyuan and Zhang, Hanwang},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2019},
pages = {6999-7006},
doi = {10.1609/AAAI.V33I01.33016999},
url = {https://mlanthology.org/aaai/2019/shi2019aaai-deepchannel/}
}