Named entity extraction via automatic labeling and tri-training: Comparison of selection methods

NCUIR > College of Electrical Engineering & Computer Science > Department of Computer Science and information Engineering > journal & Dissertation > Item 987654321/107073

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/107073

Title:	Named entity extraction via automatic labeling and tri-training: Comparison of selection methods
Authors:	張嘉惠;Chou, Chien-Lung;Chang, Chia-Hui
Contributors:	資訊電機學院資訊工程學系
Keywords:	co-labeling method;Named entity extraction;tri-training
Date:	2014-01-01
Issue Date:	2026-04-23 13:55:16 (UTC+8)
Publisher:	Springer Verlag;Cham: Springer International Publishing
Abstract:	摘要： Detecting named entities from documents is one of the most important tasks in knowledge engineering. Previous studies rely on annotated training data, which is quite expensive to obtain large training data sets, limiting the effectiveness of recognition. In this research, we propose a semi-supervised learning approach for named entity recognition (NER) via automatic labeling and tritraining which make use of unlabeled data and structured resources containing known named entities. By modifying tri-training for sequence labeling and deriving proper initialization, we can train a NER model for Web news articles automatically with satisfactory performance. In the task of Chinese personal name extraction from 8,672 news articles on the Web (with 364,685 sentences and 54,449 (11,856 distinct) person names), an F-measure of 90.4% can be achieved. 出版者： Cham: Springer International Publishing 出版日期： 2014 出處： Information Retrieval Technology, 2014, p.244-255 資源來源： Springer Books 版權： Springer International Publishing Switzerland 2014 識別號： ISSN: 0302-9743 識別號： ISBN: 9783319128436 識別號： ISBN: 3319128434 識別號： EISSN: 1611-3349 識別號： EISBN: 9783319128443 識別號： EISBN: 3319128442 識別號： DOI: 10.1007/978-3-319-12844-3_21
Appears in Collections:	[Department of Computer Science and information Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	12	View/Open

社群 sharing

Loading...