Multilayer CARU Model for Text Summarization

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

With the large amount of data available today, text summaries have become very important to get the right amount of information from a large amount of text. As can be seen, the articles in this review present different approaches to creating long summaries. Various studies have investigated different methods for summarizing text. In most cases, the methods described in this paper produce summaries or excerpt summaries of text documents, and a query-based summarization technique is also described. These techniques are structure and semantic based methods for summarizing text documents. Experimental results on the DUC-2002 dataset show that our system outperforms state of-the-art extractive and abstractive baselines on the ROUGE evaluation metric.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE International Conference on Big Data and Smart Computing, BigComp 2023
EditorsHyeran Byun, Beng Chin Ooi, Katsumi Tanaka, Sang-Won Lee, Zhixu Li, Akiyo Nadamoto, Giltae Song, Young-guk Ha, Kazutoshi Sumiya, Wu Yuncheng, Hyuk-Yoon Kwon, Takehiro Yamamoto
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages399-402
Number of pages4
ISBN (Electronic)9781665475785
DOIs
Publication statusPublished - 2023
Event2023 IEEE International Conference on Big Data and Smart Computing, BigComp 2023 - Jeju, Korea, Republic of
Duration: 13 Feb 202316 Feb 2023

Publication series

NameProceedings - 2023 IEEE International Conference on Big Data and Smart Computing, BigComp 2023

Conference

Conference2023 IEEE International Conference on Big Data and Smart Computing, BigComp 2023
Country/TerritoryKorea, Republic of
CityJeju
Period13/02/2316/02/23

Keywords

  • CARU
  • Encode-Decode Neural Network
  • NLP
  • Selector
  • Summarization

Fingerprint

Dive into the research topics of 'Multilayer CARU Model for Text Summarization'. Together they form a unique fingerprint.

Cite this