摘要
针对汉语谓语中心词识别困难及唯一性的问题,提出了一种基于Highway-BiLSTM网络的深度学习模型。首先,通过多层BiLSTM网络叠加获取句子内部不同粒度抽象语义信息的直接依赖关系;然后,利用Highway网络缓解深层模型出现的梯度消失问题;最后,通过约束层对输出路径进行规划,解决谓语中心词的唯一性问题。实验结果表明,该方法有效提升了谓语中心词识别的性能。
Aiming at the problem of difficult recognition and uniqueness of Chinese predicate head,a Highway-BiLSTM model was proposed.Firstly,multi-layer BiLSTM networks were used to capture multi-granular semantic dependence in a sentence.Then,a Highway network was adopted to alleviate the problem of gradient disappearance.Finally,the output path was optimized by a constraint layer which was designed to guarantee the uniqueness of predicate head.The experimental results show that the proposed method effectively improves the performance of predicate head recognition.
作者
黄瑞章
靳文繁
陈艳平
秦永彬
郑庆华
HUANG Ruizhang;JIN Wenfan;CHEN Yanping;QIN Yongbin;ZHENG Qinghua(College of Computer Science and Technology,Guizhou University,Guiyang 550025,China;Guizhou Provincial Key Laboratory of Public Big Data,Guiyang 550025,China;College of Computer Science and Technology,Xi’an Jiaotong University,Xi’an 710049,China)
出处
《通信学报》
EI
CSCD
北大核心
2021年第1期100-107,共8页
Journal on Communications
基金
国家自然科学基金资助项目(No.U1836205,No.91746116)
贵州省科学技术基金重点资助项目(黔科合基础[2020]1Z055)。
