摘要
属性抽取是一种自动识别和提取属性表述文字的自然语言处理任务.首先重温了属性抽取的基本任务、权威数据资源和通用评测规范,并在此基础上全面回顾了现有前沿技术,包括基于统计策略和特征工程的传统抽取技术以及利用深度学习的神经抽取技术.特别地,以属性表述语言的本质为出发点,结合现有技术暴露出的不足,对该领域的技术难点和推演方向给出了详细解释.
Aspect term extraction is a natural language processing task that automatically recognizes and extracts aspect term from free expression text.The study first goes over the basic task of aspect term extraction,the authoritative datasets of it and general evaluation specifications on it.Based on these,the study comprehensively reviews on the state-of-the-art techniques for the task,including traditional extraction techniques based on statistical strategies and feature engineering,and the neural extraction techniques using deep learning.In particular,the study takes the essence of expression language as the starting point,combines with the limitations of existing techniques and gives an elaboration of the technical difficulties and the future development prospects of aspect term extraction.
作者
徐庆婷
洪宇
潘雨晨
姚建民
周国栋
XU Qing-Ting;HONG Yu;PAN Yu-Chen;YAO Jian-Min;ZHOU Guo-Dong(School of Computer Science and Technology,Soochow University,Suzhou 215006,China)
出处
《软件学报》
EI
CSCD
北大核心
2023年第2期690-711,共22页
Journal of Software
基金
国家重点研发计划(2020YFB1313601)
国家自然科学基金(62076174,62076175)
江苏省研究生科研与实践创新计划(KYCX21_2955)。
关键词
自然语言处理
属性抽取
深度学习
natural language processing
aspect term extraction
deep learning