利用关系抽取技术联合识别文本中的方面-极性对
作者:
作者单位:

四川大学计算机学院

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:

国家重点研发项目(2020YFB0704502)


Employing relation extraction technology to jointly recognize aspect-polarity pairs in a text
Author:
Affiliation:

College of Computer Science, Sichuan University

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    方面级情感分析旨在识别出句子中显示提及的方面及其情感极性,是细粒度情感分析中的重要任务.现有使用序列标注进行方面级情感分析的方法存在当方面(aspect)由多个单词构成时,每个单词的情感极性可能不一致,而基于跨度(span)的方法存在因方面标签和情感标签混合而导致的标签异质问题,同时现有的研究忽略了文本中方面-情感极性对之间的相互关联.为了解决上述问题,受关系抽取技术的启发,本文将方面-情感极性对抽取视作一元关系抽取问题,其中方面看成论元,其对应的情感极性作为关系,通过序列解码捕捉方面-情感极性对之间的关联.本文在三个数据集上进行了一系列实验来验证模型的有效性,实验结果表明,其性能超过了现有的最佳模型.

    Abstract:

    Aspect-based sentiment analysis aims to identify the aspects mentioned in sentences and their sentiment polarity, which is an important task in fine-grained sentiment analysis. The existing studies use sequence labeling or span-based classification methods, having their own defects such as polarity inconsistency resulted from separately tagging tokens in the former and the heterogeneous categorization in the latter where aspect-related and polarity-related labels are mixed. At the same time, the existing methods ignore the correlation between aspect-polarity pairs in sentences. In order to remedy the above defects, inspiring from the recent advancements in relation extraction, we propose to generate aspect-polarity pairs directly from a text with relation extraction technology, regarding aspect-pairs as unary relations where aspects are entities and the corresponding polarities are relations and utilize sequence decoding to capture the correlation between aspect-polar pairs. The experiments performed on three benchmark datasets demonstrate that our model outperforms the existing state-of-the-art approaches.

    参考文献
    相似文献
    引证文献
引用本文

引用本文格式: 卜令梅,陈黎,卢永美,于中华. 利用关系抽取技术联合识别文本中的方面-极性对[J]. 四川大学学报: 自然科学版, 2022, 59: 012002.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-08-06
  • 最后修改日期:2021-08-19
  • 录用日期:2021-09-08
  • 在线发布日期: 2022-01-19
  • 出版日期: