Volume 8, Issue 2, September 2021, Pages 85 - 89
Comparison of Data Augmentation Methods in Pointer–Generator Model
Authors
Tomohito Ouchi*, Masayoshi Tabuse
Graduate School of Life and Environmental Sciences, Kyoto Prefectural University, 1-5 Shimogamohangi-cho, Sakyo-ku, Kyoto 606-8522, Japan
*Corresponding author. Email: t_ouchi@mei.kpu.ac.jp
Corresponding Author
Tomohito Ouchi
Received 19 October 2020, Accepted 1 May 2021, Available Online 23 July 2021.
- DOI
- 10.2991/jrnal.k.210713.003How to use a DOI?
- Keywords
- Automatic summarization; data augmentation; pointer–generator model; extractive summarization
- Abstract
In this research, we proposed a data augmentation method using topic model for Pointer–Generator model. This method is that adding important sentences to an article as extended article. Furthermore, we compare our proposed method with data augmentation methods using Easy Data Augmentation (EDA), LexRank and Luhn. EDA consists of synonym replacement, random insertion, random swap, and random deletion. LexRank is based on Google’s search method and Luhn defines sentence features and ranks sentences. We considered which method is suitable for data augmentation. We confirm that most accurate model is the model using data augmentation method by topic model.
- Copyright
- © 2021 The Authors. Published by Atlantis Press International B.V.
- Open Access
- This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Download article (PDF)
View full text (HTML)
Cite this article
TY - JOUR AU - Tomohito Ouchi AU - Masayoshi Tabuse PY - 2021 DA - 2021/07/23 TI - Comparison of Data Augmentation Methods in Pointer–Generator Model JO - Journal of Robotics, Networking and Artificial Life SP - 85 EP - 89 VL - 8 IS - 2 SN - 2352-6386 UR - https://doi.org/10.2991/jrnal.k.210713.003 DO - 10.2991/jrnal.k.210713.003 ID - Ouchi2021 ER -