| 基于深度学习的中文零代词识别 |
| |
| 引用本文： | 王立凯,曲维光,,魏庭新,周俊生,顾彦慧,李 斌.基于深度学习的中文零代词识别[J].南京师范大学学报,2021,0(4):019-26. |
| |
| 作者姓名： | 王立凯 曲维光 魏庭新 周俊生 顾彦慧 李 斌 |
| |
| 作者单位： | (1.南京师范大学计算机与电子信息学院,江苏 南京 210023)(2.南京师范大学文学院,江苏 南京 210097)(3.南京师范大学国际文化教育学院,江苏 南京 210097) |
| |
| 摘 要： | 针对中文零代词识别任务,提出了一种基于深度神经网络的中文零代词识别模型. 首先,通过注意力机制利用零代词的上下文来帮助表示缺省的语义信息. 然后,利用Tree-LSTM挖掘零代词上下文的句法结构信息. 最后,利用语义信息和句法结构信息的融合特征识别零代词. 实验结果表明,相对于以往的零代词识别方法,该方法能够有效提升识别效果,在中文OntoNotes5.0数据集上的F1值达到63.7%.
|
| 关 键 词： | 深度学习 中文零指代 零代词识别 Tree-LSTM 注意力机制 |
Identification of Chinese Zero Pronouns Based on Deep Learning |
| |
| Wang Likai,Qu Weiguang,' target="_blank" rel="external">,Wei Tingxin,Zhou Junsheng,Gu Yanhui,Li Bin.Identification of Chinese Zero Pronouns Based on Deep Learning[J].Journal of Nanjing Nor Univ: Eng and Technol,2021,0(4):019-26. |
| |
| Authors: | Wang Likai Qu Weiguang " target="_blank">' target="_blank" rel="external"> Wei Tingxin Zhou Junsheng Gu Yanhui Li Bin |
| |
| Affiliation: | (1.School of Computer and Electronic Information,Nanjing Normal University,Nanjing 210023,China)(2.School of Chinese Language and Literature,Nanjing Normal University,Nanjing 210097,China)(3.International College for Chinese Studies,Nanjing Normal University,Nanjing 210097,China) |
| |
| Abstract: | To solve the task of Chinese zero pronoun identification,this paper proposes a Chinese zero pronoun identification model based on deep neural network. Firstly,attention mechanism is applied to learn more semantic information from the context of zero pronoun. Then,Tree-LSTM is used to capture syntactic structure features of the context of the zero pronoun. Finally,semantic information and syntactic structure information are combined to identify the zero pronoun. Compared with the previous zero pronoun identification methods,experiments on Chinese OntoNotes5.0 corpus show that our proposed approach can more effectively improve the recognition effect,and the F1 value reaches 63.7%. |
| |
| Keywords: | deep learning Chinese zero pronoun zero pronoun identification Tree-LSTM attention |
|
| 点击此处可从《南京师范大学学报》浏览原始摘要信息 |
|
点击此处可从《南京师范大学学报》下载全文 |
|
