TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Text Summarization	CNN / Daily Mail (Anonymized)	GAN	ROUGE-1	39.92	# 5
Text Summarization	CNN / Daily Mail (Anonymized)	GAN	ROUGE-2	17.65	# 4
Text Summarization	CNN / Daily Mail (Anonymized)	GAN	ROUGE-L	36.71	# 7

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/generative-adversarial-network-for/text-summarization-on-cnn-daily-mail-2)](https://paperswithcode.com/sota/text-summarization-on-cnn-daily-mail-2?p=generative-adversarial-network-for)`

Generative Adversarial Network for Abstractive Text Summarization

26 Nov 2017 · Linqing Liu, Yao Lu, Min Yang, Qiang Qu, Jia Zhu, Hongyan Li ·

In this paper, we propose an adversarial process for abstractive text summarization, in which we simultaneously train a generative model G and a discriminative model D. In particular, we build the generator G as an agent of reinforcement learning, which takes the raw text as input and predicts the abstractive summarization. We also build a discriminator which attempts to distinguish the generated summary from the ground truth summary. Extensive experiments demonstrate that our model achieves competitive ROUGE scores with the state-of-the-art methods on CNN/Daily Mail dataset. Qualitatively, we show that our model is able to generate more abstractive, readable and diverse summaries.

PDF Abstract