Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Research of Paragraphs Segmentation and Elements Recognition for Academic Papers Based on Multi-features

Liu Huoyu;Wang Dongbo;Su Xinning;School of Information Management of Nanjing University;Jiangsu Key Laboratory of Data Engineering and Knowledge Service;College of Information and Technology,of Nanjing Agricultural University;  
The article provides a valuable method for the academic papers' structuration process.It summaries original academic papers' local and global features and uses the complex feature template to the task of paragraphs segmentation and elements recognition based on CRFs.In open tests,the best F value can reach 88%and 92%respectively.Based on the comparison between CRFs and ME,the article gains the conclusion that the effect of CRFs is more excellent than ME but costs more time.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved