메뉴 건너뛰기
Library Notice
Institutional Access
If you certify, you can access the articles for free.
Check out your institutions.
ex)Hankuk University, Nuri Motors
Log in Register Help KOR
Subject

Stepwise Summarization through Splitting Sentences for Long-document Summarization
Recommendations
Search
Questions

긴 문서 요약을 위한 문장 분할 기반의 단계적 요약

논문 기본 정보

Type
Proceeding
Author
Seojin Lee (중앙대학교) Hwanhee Lee (중앙대학교)
Journal
The Institute of Electronics and Information Engineers 대한전자공학회 학술대회 2024년도 대한전자공학회 하계학술대회 논문집
Published
2024.6
Pages
2,849 - 2,852 (4page)

Usage

cover
📌
Topic
📖
Background
🔬
Method
🏆
Result
Stepwise Summarization through Splitting Sentences for Long-document Summarization
Ask AI
Recommendations
Search
Questions

Abstract· Keywords

Report Errors
Transformer based pre-trained language models have shown high performance across various NLP tasks, especially for summarization. However, the limit of input sequence length causes difficulties that only capture the beginning part of documents when such texts exceed the maximum sequence length of the model. This paper proposes a stepwise summarization approach by splitting lengthy documents into pieces, which makes it possible for the model to efficiently summarize long articles by capturing entire context. We fine-tune a BART model on a specific dataset to enhance the quality of summary. The experiment demonstrates that proposed approach has advantages in readability and provides the potential for future abstractive summarization research.

Contents

Abstract
Ⅰ. 서론
Ⅱ. 본론
Ⅲ. 실험
Ⅴ. 결론 및 향후 연구 방향
참고문헌

References (0)

Add References

Recommendations

It is an article recommended by DBpia according to the article similarity. Check out the related articles!

Recently viewed articles

Comments(0)

0

Write first comments.