版权说明 操作指南
首页 > 成果 > 详情

Enhanced dual-level dependency parsing for aspect-based sentiment analysis

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Zhang, Maoyuan;Liu, Lisha;Mi, Jiaxin;Yuan, Xianqi
通讯作者:
Lisha Liu
作者机构:
[Liu, Lisha; Zhang, Maoyuan] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smar, Wuhan 430079, Peoples R China.
[Mi, Jiaxin; Liu, Lisha; Zhang, Maoyuan; Yuan, Xianqi] Cent China Normal Univ, Sch Comp, Wuhan 430079, Hubei, Peoples R China.
[Yuan, Xianqi] Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netw, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Lisha Liu] H
Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, Wuhan, Hubei, China<&wdkj&>School of Computer, Central China Normal University, Wuhan, Hubei, China
语种:
英文
关键词:
Aspect-based sentiment analysis;Dependency tree;Dual-level dependency parsing;Gaussian context dynamic weighting;Graph attention network
期刊:
JOURNAL OF SUPERCOMPUTING
ISSN:
0920-8542
年:
2023
卷:
79
期:
6
页码:
6290-6308
机构署名:
本校为第一机构
院系归属:
计算机学院
摘要:
Aspect-Based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task, aiming at mining sentiment polarity towards specific aspects. Most existing work to address ABSA has focused on using Graph Neural Networks combined with syntactic dependency trees. However, existing models often fall into semantic confusion for sentiment analysis due to the information imbalance in the dependency tree. To solve the problem of semantic confusion, we propose a Local Enhanced Relational Graph Attention Network with Dual-level Dependency Parsing (DL-...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com