Research on Tibetan Culture Domain Entity Recognition

DOI

10.2991/iccsae-15.2016.161How to use a DOI?

Keywords

Named Entity Recognition; Tibetan Culture Domain; Bootstrapping; Maximum Entropy.

Abstract

Named Entity Recognition (NER) is the premise of other tasks in Information Extraction. At present, most NER studies are focus on person names, place names and organization names. However, domain entity recognition is still a challenging task. Tibetan culture domain entity recognition has important significance for studying Tibetan culture. This article extracts domain keywords based on improved TextRank algorithm. Then domain words bank is structured using domain keywords, and word segmentation is conducted. On the basis, Tibetan culture domain entities are recognized based on the improved Bootstrapping. The method in this article has better extracting performance and good generalization.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yinghui Feng
AU  - Zhijuan Wang
PY  - 2016/02
DA  - 2016/02
TI  - Research on Tibetan Culture Domain Entity Recognition
BT  - Proceedings of the 2015 5th International Conference on Computer Sciences and Automation Engineering
PB  - Atlantis Press
SP  - 867
EP  - 872
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccsae-15.2016.161
DO  - 10.2991/iccsae-15.2016.161
ID  - Feng2016/02
ER  -