arrow
返回

Multi-Encoder Transformer for Korean Abstractive Text Summarization

delete2023-01-01
delete3
delete
OA
AI
Y
Youhyun Shin *
DOI:10.1109/ACCESS.2023.3277754delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
In this paper, we propose a Korean abstractive text summarization approach that uses a multi -encoder transformer. Recently, in many natural language processing (NLP) tasks, the use of the pre-trained language models (PLMs) for transfer learning has achieved remarkable performance. In particular, transformer-based models such as Bidirectional Encoder Representations from Transformers (BERT) are used for pre-training and applied to downstream tasks, showing state-of-the-art performance including abstractive text summarization. However, existing text summarization models usually use one pre-trained model per model architecture, meaning that it becomes necessary to choose one PLM at a time. For PLMs applicable to Korean abstractive text summarization, there are publicly available BERT-based pre-trained Korean models that offer different advantages such as Multilingual BERT, KoBERT, HanBERT, and KorBERT. We assume that if these PLMs could be leveraged simultaneously, better performance would be obtained. We propose a model that uses multiple encoders which are capable of leveraging multiple pre-trained models to create an abstractive summary. We evaluate our method using three benchmark Korean abstractive summarization datasets, each named Law (AI-Hub), News (AI-Hub), and News (NIKL) datasets. Experimental results show that the proposed multi-encoder model variations outperform single -encoder models. We find the empirically best summarization model by determining the optimal input combination when leveraging multiple PLMs with the multi-encoder method.
Keyword:
Natural language processing
abstractive text summarization
bidirectional encoder repre-sentations from transformer
neural networks
natural language generation

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

I
incheon national university
学者数:
4.0K
论文数: 4.3K
被引数: 4
引用论文

引用论文

SCALING WITH KNOWN UNCERTAINTY: A SYNTHESIS
err2006-01-01
err0
PREAI
errJIANGUO WU; HARBIN LI; K. BRUCE JONES; ORIE L. LOUCKS
err分享
err收藏
err分享
err收藏
Caveolin-1 and -2 regulate cell motility in castration-resistant prostate cancer
err2018-10-01
err0
errOAAI
errToyoharu Kamibeppu; Koji Yamasaki; Kozue Nakahara; Takahiro Nagai; Naoki Terada; Hiromasa Tsukino; Shoichiro Mukai; Toshiyuki Kamoto
err分享
err收藏
Interaction of Tau Isoforms with Alzheimer's Disease Abnormally Hyperphosphorylated Tau and in VitroPhosphorylation into the Disease-like Protein
err2001-10-01
err0
errOAAI
errAlejandra del C. Alonso; Tanweer Zaidi; Michal Novak; Hector S. Barra; Inge Grundke-Iqbal; Khalid Iqbal
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
First United States Outbreak of Mycobacterium abscessus Hand and Foot Disease Among Children Associated With a Wading Pool
err2018-05-29
err0
errOAAI
errKris K Carter; Ingrid Lundgren; Sarah Correll; Tom Schmalz; Tammie McCarter; Joshua Stroud; Amanda Bruesch; Christine G Hahn
err分享
err收藏
Sucrose Preference and Novelty-Induced Hypophagia Tests in Rats using an Automated Food Intake Monitoring System使用自动化食物摄入监测系统进行的蔗糖偏好和 novelty-induced hypophagia 测试
err2020-05-08
err0
PREAI
errMartha Anna Schalla; Stephanie Gladys Kühne; Tiemo Friedrich; Vivien Hanel; Peter Kobelt; Miriam Goebel-Stengel; Matthias Rose; Andreas Stengel
err分享
err收藏
学者 查看更多内容