ITM Web Conf.
Volume 12, 2017The 4th Annual International Conference on Information Technology and Applications (ITA 2017)
|Number of page(s)||7|
|Section||Session 4: Information Theory and Information Systems|
|Published online||05 September 2017|
Collective Entity Linking Method in Chinese Text Based on Topic Consistency
School of Computer, National University of Defense Technology, Changsha, China 0731
Entity Linking refers to the task of linking entity mentions in the given text with their referent entities in a knowledge base, which is a key technology of knowledge base expansion. However, the performance of traditional Chinese entity linking methods are affected by the incomplete Chinese knowledge base. Also they rarely use the semantic relevance between entities. Therefore, we propose a Chinese collective entity linking method based on the consistency of the topic, which considers both the content similarity and topic relevance of the co-occurrence entities, and propose a method for calculating the topic consistency of entities. This method implements batch links for multiple ambiguous entities that appear in the same text, and reduces the reliance on the local knowledge base by using the combination of the local knowledge base and the external knowledge base. Experimental results show that our method performs well over the traditional methods. And it is potentially effective.
© The Authors, published by EDP Sciences, 2017
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.