Enhancing global features for Chinese named entity recognition
In English,global features of each word in a document can effectively enhance entity recognition.Unlike English,Chinese does not have explicit delimiters,and the basic unit of learning for models is characters rather than words.Therefore,intro-ducing global features for characters increases the difficulty of model learning.To address this issue,after the model extracts con-textual representations for each character,it first obtains different contextual representations for each character within the docu-ment.Then,multiple filters are applied to these different contextual representations.Finally,a gated attention mechanism controls the prediction weight of the global features.Experimental results show that the proposed model outperforms baseline models on the Resume,Weibo,and Ontonotes 4.0 datasets.
Chinese named entity recognitionglobal featuresfiltering mechanismgating attention
万方数据
