基于多级别特征感知网络的中文命名实体识别  

Chinese Named Entity Recognition Method Based on Multi-level Feature Perception Network

作　　者：宋威 周俊昊 SONG Wei;ZHOU Junhao(School of Artificial Intelligence and Computer Science,Jiangnan University,Wuxi,Jiangsu 214122,China;Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence,JiangnanUniversity,Wuxi,Jiangsu 214122,China)

机构地区：[1]江南大学人工智能与计算机学院,江苏无锡214122 [2]江南大学江苏省模式识别与计算智能工程实验室,江苏无锡214122

出　　处：《中文信息学报》2022年第9期84-92,共9页Journal of Chinese Information Processing

基　　金：国家自然科学基金(61673193,62076110);江苏省自然科学基金(BK20181341);中国博士后科学基金(2017M621625)。

摘　　要：当前中文命名实体识别方法仅采用字级别或词级别特征方法进行识别,不能兼顾字和词级别的优点,难以获取足够的字形或者词义信息。针对此问题,该文提出一种基于多级别特征感知网络的中文命名实体识别方法。首先提出一种双通道门控卷积神经网络,通过感知字级别特征,在减少了未登录词的同时,也表示了字的字形信息。同时,为了获取词语的词义信息,该文在词级别的特征中嵌入对应位置信息。为了赋予实体更多的权重,该文利用自注意力机制感知带有位置信息的词级别特征。进一步,将上述得到的字级别和词级别信息融合,全面表示句子的语义信息。由于采用字词结合的方法容易产生冗余信息,该文设计一种门控机制的Highway网络,来过滤冗余信息,减少冗余信息对命名实体识别的影响,再结合条件随机场学习到句子中的约束条件实现中文命名实体的识别。实验结果表明,该文所提出的方法总体上优于目前主流的中文命名实体识别方法。Currently most Chinese named entity recognition methods use either Chinese character-level or word-level feature-aware networks for recognition.In this condition,the advantages of both character-level and word-level methods cannot be combined together,which makes it difficult to obtain adequate information of the Chinese character glyphs or the word semantics.This paper proposes a Chinese named entity recognition method based on multi-level feature-aware network.Firstly,a two-channel gated convolutional neural network is proposed to perceive Chinese character-level features,which alleviates the OOV(out-of-vocabulary)words and obtains the glyph information of Chinese characters.To apply entities with more weights,the self-attention mechanism is used to perceive the word semantics with position information.Therefore,the Chinese character-level and word-level information obtained above are fused,with a Highway network based on the gating mechanism to filter the redundant information.Finally,the Conditional Random Field is applied to learn the constraints in the sentence.The experimental results show that the proposed algorithm performs better than the current mainstream Chinese named entity recognition algorithms.

关 键 词：命名实体识别 双通道门控卷积 自注意力机制 Highway网络 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]