Unsupervised Abstractive Summarization Method that Suitable for Documents with Flows


KIPS Transactions on Software and Data Engineering, Vol. 10, No. 11, pp. 501-512, Nov. 2021
https://doi.org/10.3745/KTSDE.2021.10.11.501,   PDF Download:  
Keywords: NLP, summarization, GAN, BERT, Transformer
Abstract

Recently, a breakthrough has been made in the NLP area by Transformer techniques based on encoder-decoder. However, this only can be used in mainstream languages where millions of dataset are well-equipped, such as English and Chinese, and there is a limitation that it cannot be used in non-mainstream languages where dataset are not established. In addition, there is a deflection problem that focuses on the beginning of the document in mechanical summarization. Therefore, these methods are not suitable for documents with flows such as fairy tales and novels. In this paper, we propose a hybrid summarization method that does not require a dataset and improves the deflection problem using GAN with two adaptive discriminators. We evaluate our model on the CNN/Daily Mail dataset to verify an objective validity. Also, we proved that the model has valid performance in Korean, one of the non-mainstream languages.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
H. Lee, S. An, S. Kim, "Unsupervised Abstractive Summarization Method that Suitable for Documents with Flows," KIPS Transactions on Software and Data Engineering, vol. 10, no. 11, pp. 501-512, 2021. DOI: https://doi.org/10.3745/KTSDE.2021.10.11.501.

[ACM Style]
Hoon-suk Lee, Soon-hong An, and Seung-hoon Kim. 2021. Unsupervised Abstractive Summarization Method that Suitable for Documents with Flows. KIPS Transactions on Software and Data Engineering, 10, 11, (2021), 501-512. DOI: https://doi.org/10.3745/KTSDE.2021.10.11.501.