|陈玉博1; 何世柱1; 刘康1; 赵军1; 吕学强2|
Named entity disambiguation is one of the key techniques in naturallanguage processing. lt aims at resolving
the name ambiguity problem which is common in the textual information and plays an important role in many
different areas , such as information retrieval , knowledge engineering and semantic web. Entity linking is an impor
tant method of entity disambiguation , which aims to map an entity to an entry stored in the existing knowledge base.
Several methods have been proposed to tackle this probl em , but they a re largely based on the co-occurrence statistics
of terms between the text around the entity mention and the document associated with the entity. It can't capture va
rious semantic relations. To capture more semantic relations , in this paper we make use of multiple features. To
make the best use of the features , we propose a learning to rank algorithm for entity linking. lt effectively utilizes
the relationship information among the candidates and save a lot of time and effort. The experiment results on the
T AC KBP 2009 dataset demonstrate the effectiveness of our proposed features and framework. The accuracy on the
dataset is 84.38% , exceeding the best result of the TAC KBP 2009 by 2. 21%.
|Keyword||实体消歧 实体链接 排序学习|
|陈玉博,何世柱,刘康,等. 融合多种特征的实体链接技术研究[J]. 中文信息学报,2016,30(4):176-183.|
|MLA||陈玉博,et al."融合多种特征的实体链接技术研究".中文信息学报 30.4(2016):176-183.|
|Files in This Item:||Download All|
|融合多种特征的实体链接技术研究_陈玉博.（473KB）||期刊论文||作者接受稿||开放获取||CC BY-NC-SA||View Download|
|Recommend this item|
|Export to Endnote|
|Similar articles in Google Scholar|
|Similar articles in Baidu academic|
|Similar articles in Bing Scholar|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.