.png){kind=icon}
.png){kind=icon}
Return
Abstractive text summarization using adversarial learning and deep neural network
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-023-17478-0.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A long-term objective of artificial intelligence is to design an abstractive text summarization (ATS) system that can produce condensed, adequate, and realistic summaries for the source documents. Deep learning approaches have contributed significantly to recent advancements in ATS, taking the state-of-the-art to new heights. Despite the considerable success of earlier approaches, producing high-quality and more human-like abstractive summaries continues to be a challenging task in reality. In this paper, we present an adversarial framework for abstractive text summarization, in which a generative model G and a proposed deep discriminative model D are trained in an adversarial manner. The goal of the generator is to generate summaries that are hard to differentiate from real summaries, whereas the discriminator's role is to estimate the probability that a summary came from the training data rather than the generator to direct the generative model's training. Experimental results on a benchmark CNN/Daily Mail dataset demonstrate that the proposed model achieves Rouge-1 and Rouge-L scores of 41.58 and 38.96 respectively which are better than the ones reported by various other methods (e.g. the base paper [1] achieved Rouge-1 and Rouge-L score of 39.92 and 36.71, while one of the recent works ACGT [2] achieved Rouge-1 score of 40.49 and Rouge-L score of 37.41). The manuscript's unique characteristic is qualitative evaluation, which, along with quantitative evaluation, shows that the proposed model is superior.
Keywords:
Abstractive text summarization
Deep neural networks
Generative adversarial networks
Adversarial learning
Natural language processing
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W