| Title: | OS7-1 Effectiveness of Data Augmentation in Automatic Summarization System |
|---|---|
| Publication: | ICAROB2019 |
| Volume: | 24 |
| Pages: | 177-180 |
| ISSN: | 2188-7829 |
| DOI: | 10.5954/ICAROB.2019.OS7-1 |
| Author(s): | Tomohito Ouchi, Masayoshi Tabuse |
| Publication Date: | January 10, 2019 |
| Keywords: | automatic summarization, data augmentation, encoder-decoder model, attention mechanism |
| Abstract: | We propose a new data augmentation method in automatic summarization system. A large corpus is required to create an automatic summarization system using deep learning. However, in the field of natural language processing, especially in the field of automatic summarization, there are not many data sets that are sufficient to train automatic summarization system. Therefore, we propose a new method of data augmentation. We use an encoder-decoder model with an attention mechanism as automatic summarization system. First, we determine the importance of each sentence in an article using topic model. In order to extend the data, we remove the least important sentence from an input article and use it as a new article. We examine the effectiveness of our proposed data augmentation method in automatic summarization system. |
| PDF File: | https://alife-robotics.co.jp/members2019/icarob/data/html/data/OS_pdf/OS7/OS7-1.pdf |
| Copyright: | © The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/ |
(c)2008 Copyright The Regents of ALife Robotics Corporation Ltd. All Rights Reserved.