A Rule System for Chinese Time Entity Recognition by Comprehensive Linguistic Study
Hongzhi Xu, Chu‐Ren Huang · International Joint Conference on Natural Language Processing · 2013
Chinese time entity is quite complex. In this paper, we give a comprehensive linguistic study on it. Based on the analysis, we present a rule system which only considers the inner structure of Chinese time entities for the recognition. Experiments on Sinica and TempEval-2 corpus show that the rule system performs much better than the CRFs model. When using the rules as features within a CRFs model, the performance could be further improved.