| 基于Highway-BiLSTM网络的汉语谓语中心词识别研究 |
| |
| 引用本文： | 黄瑞章,靳文繁,陈艳平,秦永彬,郑庆华.基于Highway-BiLSTM网络的汉语谓语中心词识别研究[J].通信学报,2021(1):100-107. |
| |
| 作者姓名： | 黄瑞章 靳文繁 陈艳平 秦永彬 郑庆华 |
| |
| 作者单位： | 贵州大学计算机科学与技术学院;贵州省公共大数据重点实验室;西安交通大学计算机科学与技术学院 |
| |
| 基金项目： | 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)。 |
| |
| 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...
|
| 关 键 词： | 谓语中心词 高速公路连接 双向长短期记忆网络 唯一性 |
Research on Chinese predicate head recognition based on Highway-BiLSTM network |
| |
| HUANG Ruizhang,JIN Wenfan,CHEN Yanping,QIN Yongbin,ZHENG Qinghua.Research on Chinese predicate head recognition based on Highway-BiLSTM network[J].Journal on Communications,2021(1):100-107. |
| |
| Authors: | HUANG Ruizhang JIN Wenfan CHEN Yanping QIN Yongbin ZHENG Qinghua |
| |
| Affiliation: | (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) |
| |
| Abstract: | 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. |
| |
| Keywords: | predicate head highway connection BiLSTM uniqueness |
| 本文献已被 维普 等数据库收录！ |
|
