计算机工程与应用 ›› 2023, Vol. 59 ›› Issue (9): 167-175.DOI: 10.3778/j.issn.1002-8331.2201-0088

• 模式识别与人工智能 • 上一篇    下一篇

结合Hybrid Attention机制和BiLSTM-CRF的汉语否定语义表示及标注

李晋荣,吕国英,李茹,柴清华,王超   

  1. 1.山西大学 计算机与信息技术学院,太原 030006
    2.山西大学 计算智能与中文信息处理教育部重点实验室,太原 030006
    3.山西大学 外国语学院,太原 030006
  • 出版日期:2023-05-01 发布日期:2023-05-01

Chinese Negative Semantic Representation and Annotation Combined with Hybrid Attention Mechanism and BiLSTM-CRF

LI Jinrong, LYU Guoying, LI Ru, CHAI Qinghua, WANG Chao   

  1. 1.College of Computer and Information Technology, Shanxi University, Taiyuan 030006, China
    2.Key Laboratory of Computer Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan 030006, China
    3.School of Foreign Languages, Shanxi University, Taiyuan 030006, China
  • Online:2023-05-01 Published:2023-05-01

摘要: 阅读理解中否定是一种复杂的语言现象,其往往会反转情感或态度的极性。因此,正确分析否定语义对语篇理解具有重要意义。现有否定语义分析方法存在两个问题:第一,研究的否定词较少达不到应用目的;第二,目前汉语否定语义标注只是标注整个句子,这无法明确否定语义。针对该问题提出基于汉语框架语义知识库(Chinese FrameNet)进行否定语义角色标注方法。在框架语义学理论指导下结合汉语否定语义特征对已由FrameNet继承的否定框架重新构建;为了解决捕捉长距离信息以及句法特征问题,提出一种基于Hybrid Attention机制的BiLSTM-CRF语义角色标注模型,其中,Hybrid Attention机制层将局部注意与全局注意结合准确表示句子中的否定语义,BiLSTM网络层自动学习并提取语句上下文信息,CRF层预测最优否定语义角色标签。经过比对验证,该模型能够有效提取出含有否定语义信息,在否定语义框架数据集上F1值达到89.82%。

关键词: 汉语框架语义知识库, 语义角色标注, 否定框架, 双向长短期记忆网络, 混合注意力机制

Abstract: Negation is a complex language phenomenon in reading comprehension, which often reverses the polarity of emotion or attitude. Therefore, the correct analysis of negative semantics is of great significance to discourse understanding. There are two problems in the existing negative semantic analysis methods:first, there are few negative words, which can not achieve the purpose of application. Second, at present, Chinese negative semantic tagging is only tagging the whole sentence, which can not clarify the negative semantics. To solve this problem, a negative semantic role annotation method based on Chinese FrameNet is proposed. Firstly, under the guidance of frame semantics theory, combined with the semantic characteristics of Chinese negation, the negative framework inherited by FrameNet is reconstructed. Secondly, in order to solve the problem of capturing long-distance information and syntactic features, a BiLSTM-CRF semantic role annotation model based on Hybrid Attention mechanism is proposed. The Hybrid Attention mechanism layer combines local attention and global attention to accurately represent the negative semantics in the sentence, the BiLSTM network layer automatically learns and extracts the sentence context information, and the CRF layer predicts the optimal negative semantic role label. Through comparison and verification, the model can effectively extract negative semantic information, and the F1 value reaches 89.82% on the negative semantic framework data set.

Key words: Chinese framework knowledge base, semantic role annotation, negation frame, bi-directional long short-term memory(BiLSTM), hybrid attention mechanism