DocumentCode :
234817
Title :
Domain-Specific Product Named Entity Recognition from Chinese Microblog
Author :
Xianxiang Yang ; Heyan Huang ; Xin Xin ; Quanchao Liu ; Xiaochi Wei
Author_Institution :
Sch. of Comput. Sci. & Technol., Beijing Inst. of Technol., Beijing, China
fYear :
2014
fDate :
15-16 Nov. 2014
Firstpage :
218
Lastpage :
222
Abstract :
In this paper, we presented an effective method to recognize product named entity from Chinese micro blog. Due to the short, noisy and informal text, it is much more difficult to recognize Pro-NEs from micro blog than traditional media, such as news articles. In order to work out the challenges, we carried out a statistical analysis on the appearance of Pro-NEs in Chinese micro blog, According to the structure of Pro-NEs, we integrated some features and introduced external knowledge to the conditional random fields model. Experiments on an artificial annotated micro blog corpus show that our approach can improve the performance of the product named entity recognition from microblog.
Keywords :
information retrieval; social networking (online); statistical analysis; Chinese microblog; Pro-NE; artificial annotated micro blog corpus; conditional random field model; domain-specific product named entity recognition; external knowledge; statistical analysis; Cellular phones; Companies; Computational linguistics; Context; Hidden Markov models; Media; Text recognition; CRFs; Chinese; microblog; product named entity recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence and Security (CIS), 2014 Tenth International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4799-7433-7
Type :
conf
DOI :
10.1109/CIS.2014.73
Filename :
7016887
Link To Document :
بازگشت