Disambiguating named entities with deep supervised learning via crowd labels

详细信息    查看全文

• 作者：Le-kui Zhou ; Si-liang Tang ; Jun Xiao ; Fei Wu…
• 关键词：Key wordsNamed entity disambiguation ; Crowdsourcing ; Deep learning
• 刊名：Frontiers of Information Technology & Electronic Engineering
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：18
• 期：1
• 页码：97-106
• 全文大小：
• 刊物类别：Computer Science, general; Electrical Engineering; Computer Hardware; Computer Systems Organization
• 刊物主题：Computer Science, general; Electrical Engineering; Computer Hardware; Computer Systems Organization and Communication Networks; Electronics and Microelectronics, Instrumentation; Communications Engine
• 出版者：Zhejiang University Press
• ISSN：2095-9230
• 卷排序：18

文摘

Named entity disambiguation (NED) is the task of linking mentions of ambiguous entities to their referenced entities in a knowledge base such as Wikipedia. We propose an approach to effectively disentangle the discriminative features in the manner of collaborative utilization of collective wisdom (via human-labeled crowd labels) and deep learning (via human-generated data) for the NED task. In particular, we devise a crowd model to elicit the underlying features (crowd features) from crowd labels that indicate a matching candidate for each mention, and then use the crowd features to fine-tune a dynamic convolutional neural network (DCNN). The learned DCNN is employed to obtain deep crowd features to enhance traditional hand-crafted features for the NED task. The proposed method substantially benefits from the utilization of crowd knowledge (via crowd labels) into a generic deep learning for the NED task. Experimental analysis demonstrates that the proposed approach is superior to the traditional hand-crafted features when enough crowd labels are gathered.