• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neurocomputing >Integrate syntax information for target-oriented opinion words extraction with target-specific graph convolutional network
【24h】

Integrate syntax information for target-oriented opinion words extraction with target-specific graph convolutional network

机译：与目标特定的图形卷积网络集成了目标导向的观点词提取的语法信息

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Target-oriented Opinion Words Extraction (TOWE) aims to identify opinion words toward a specific target given the sentence. Syntax structure, which contains dependency relationships among words, is a vital clue for this task. With the help of syntax structure as a constraint, the model could remove irrelevant words and focus on tokens that are relevant to the given target. Directly adapting existing syntactic based methods faces the problem that these models do not explicitly learn target-centric representations. Another challenge is that prior works only learn fixed order dependency relations, while context words require syntactic information in different scales. To handle these issues, we propose Target-Specific Graph Convolutional Network (TS-GCN) to explicitly integrate dependency structure. The proposed method could build high-quality syntax-aware representations by propagating target information to syntactically related words via graph convolution. Furthermore, we design a memory-based module to dynamically learn multi-granularity syntactic knowledge and infuse local features. Experimental results demonstrate the effectiveness of our method, and we achieve state-of-the-art performances on four SemEval datasets.(c) 2021 Published by Elsevier B.V.
机译：面向目标的意见单词提取（TOWE）旨在识别给予判决的特定目标的意见话语。语法结构包含单词之间的依赖关系，是这项任务的重要线索。在语法结构的帮助下作为约束，模型可以删除无关的单词并侧重于与给定目标相关的令牌。直接调整现有的语法为基础的方法面临着这些模型没有明确学习目标为中心的交涉的问题。另一个挑战是，事先作品只学习固定订单依赖关系，而上下文单词需要不同尺度的语法信息。为了处理这些问题，我们提出了特定于目标的图形卷积网络（TS-GCN）以明确地集成依赖结构。该方法可以通过通过图表卷积将目标信息传播到句法相关的单词来构建高质量的语法感知表示。此外，我们设计基于内存的模块，动态地学习多粒度句法知识并注入本地功能。实验结果表明了我们方法的有效性，我们在四个半数据集上实现了最先进的表演。（c）由elsevier b.v发布的2021年。

著录项

  • 来源
    《Neurocomputing》 |2021年第14期|321-335|共15页
  • 作者

    Zhang Jingyuan; Li Feng; Zhang Zequn; Xu Guangluan; Wang Yang; Wang Xinyi; Zhang Yunyan;

  • 作者单位

    Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China|Chinese Acad Sci Key Lab Network Informat Syst Technol NIST Aerosp Informat Res Inst Beijing 100190 Peoples R China|Univ Chinese Acad Sci Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100190 Peoples R China;

    Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China|Chinese Acad Sci Key Lab Network Informat Syst Technol NIST Aerosp Informat Res Inst Beijing 100190 Peoples R China;

    Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China|Chinese Acad Sci Key Lab Network Informat Syst Technol NIST Aerosp Informat Res Inst Beijing 100190 Peoples R China;

    Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China|Chinese Acad Sci Key Lab Network Informat Syst Technol NIST Aerosp Informat Res Inst Beijing 100190 Peoples R China;

    Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China|Chinese Acad Sci Key Lab Network Informat Syst Technol NIST Aerosp Informat Res Inst Beijing 100190 Peoples R China;

    Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China|Chinese Acad Sci Key Lab Network Informat Syst Technol NIST Aerosp Informat Res Inst Beijing 100190 Peoples R China|Univ Chinese Acad Sci Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100190 Peoples R China;

    Chinese Acad Sci Aerosp Informat Res Inst Beijing 100190 Peoples R China|Chinese Acad Sci Key Lab Network Informat Syst Technol NIST Aerosp Informat Res Inst Beijing 100190 Peoples R China|Univ Chinese Acad Sci Beijing 100190 Peoples R China|Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100190 Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Opinion extraction; Syntax information; Graph convolutional network;

    机译：意见提取;语法信息;图卷积网络;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号