Open AccessJournal Article
Web News Multi-document Summarization Based on Event Extraction
Reads0
Chats0
TLDR
The event extraction technology is introduced and an event extraction based web news multi-document summarization method is proposed, which improves summarization quality significantly.Abstract:
State-of-the-art automatic summarization is based on text segment clustering to avoid redundancy defects in the traditional approachesBut some of the text segments in the web news are irrelevant to the subject,which affects the result of clustering and damages the conciseness of summarizationThis paper introduces the event extraction technology and proposes an event extraction based web news multi-document summarization methodFirstly,the method distinguishes event and non-event from the news through a binary classifierThen,the original documents' physical division based on paragraphs or sentences are transformed into event based content logical division through clusteringFinally,the summarization is derived from the extraction,taxis and embellishment of the major eventsExperimental results demonstrate the effectiveness of the proposed method,which improves summarization quality significantlyread more
Citations
More filters
Journal ArticleDOI
Summary Extract Approach of Heterogeneous Multimedia Documents Based on Folksonomy with Incentive and Quality Assurance Mechanisms
Jin-Bo Bai,Hong-Bo Li,Xu Sun,Shu-Sen Dong,Lei-Lei Kong,Chang-Wei Wu,Hong Deng,Feng Zhao,Yan-Yan Zhang +8 more
TL;DR: The proven folksonomy ensures the practicality of the approach, the incentive and quality assurance mechanisms avoid the innate problems of folksonomy: cold boot and inaccurate tagging.
A New Method for Text Summary Extract Base on Event Network
TL;DR: The experimental results show that extraction method of automatic summary based on the event network has achieved better performance.
Journal ArticleDOI
Enhancing LLM with Evolutionary Fine Tuning for News Summary Generation
Le Xiao,Xiaolin Chen +1 more
TL;DR: In this article , the authors proposed a new paradigm for news summary generation using LLM with powerful natural language understanding and generative capabilities, which can provide accurate and comprehensive information to help people better understand and respond to complex real-world events.
Journal ArticleDOI
Enhancing LLM with Evolutionary Fine Tuning for News Summary Generation
Xiaolin Chen,Le Xiao +1 more
TL;DR: In this paper , the authors proposed a new paradigm for news summary generation using LLM with powerful natural language understanding and generative capabilities, which can provide accurate and comprehensive information to help people better understand and respond to complex real-world events.
References
More filters
Journal ArticleDOI
Summary Extract Approach of Heterogeneous Multimedia Documents Based on Folksonomy with Incentive and Quality Assurance Mechanisms
Jin-Bo Bai,Hong-Bo Li,Xu Sun,Shu-Sen Dong,Lei-Lei Kong,Chang-Wei Wu,Hong Deng,Feng Zhao,Yan-Yan Zhang +8 more
TL;DR: The proven folksonomy ensures the practicality of the approach, the incentive and quality assurance mechanisms avoid the innate problems of folksonomy: cold boot and inaccurate tagging.
A New Method for Text Summary Extract Base on Event Network
TL;DR: The experimental results show that extraction method of automatic summary based on the event network has achieved better performance.