Work

Generative Adversarial Network for Abstractive Text Summarization

Year: 2018
Type: conference-paper
Abstract: 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.
Language: English
Open Access status: diamond
OpenAlex ID: W2963521413
FWCI: 10.03
Cites: 7
Cited by: 206
Related to: 10