ConAs-GRNs: Sentiment Classification with Construction-Assisted Multi-Scale Graph Reasoning Networks

ConAs-GRNs: Sentiment Classification with Construction-Assisted Multi-Scale Graph Reasoning Networks
复制标题

ConAs-GRN:利用构建辅助的多尺度图推理网络进行情感分类

DOI:
10.3390/electronics11121825
复制
发表时间:
2022-06
期刊:
影响因子:
2.9
通讯作者:
Jihua Song
Jihua Song
中科院分区:
工程技术3区
文献类型:
--
作者:
Bo Chen;Weiming Peng;Jihua Song

文献摘要

参考文献

相似文献

传统的神经网络在对情感文本的精细全局和上下文语义进行建模方面能力有限,并且通常忽略不同情感词之间的依赖关系。为了解决这一局限性,本文提出了一种构建辅助的多尺度图推理网络(ConAs-GRNs),该网络通过关注显着的情感信息,从多个方面探索上下文语义的细节以及情感文本之间的情感依赖关系。在该网络中,使用基于情感构建的多尺度拓扑图来描述情感依赖的多个方面,并利用句子依赖树来构建基于情感词和文本的关系图。然后,对拓扑图进行迁移学习和池化学习。在我们的例子中,加权边缘缩减策略用于聚合邻接信息,从而实现单个图中语义信息的内部传输。此外,为了实现语义信息的图间传递,我们依靠构造结构来协调异构图信息。在两个基线数据集 SemEval 2014 和 ACL-14 上进行的广泛实验表明,所提出的 ConAs-GRN 可以有效地协调和集成结构内的异构信息。
Traditional neural networks have limited capabilities in modeling the refined global and contextual semantics of emotional texts and usually ignore the dependencies between different emotional words. To address this limitation, this paper proposes a construction-assisted multi-scale graph reasoning network (ConAs-GRNs), which explores the details of the contextual semantics as well as the emotional dependencies between emotional texts from multiple aspects by focusing on the salient emotional information. In this network, an emotional construction-based multi-scale topological graph is used to describe multiple aspects of emotional dependency, and a sentence dependency tree is utilized to construct a relationship graph based on emotional words and texts. Then, the transfer learning and pooling learning on the topology map is performed. In our case, a weighted edge reduction strategy is used to aggregate the adjacency information which enables the internal transfer of semantic information in a single graph. Moreover, to implement the inter-graph transfer of semantic information, we rely on the construction structure to coordinate the heterogeneous graph information. The extensive experiments conducted on two baseline datasets, SemEval 2014 and ACL-14, demonstrate that the proposed ConAs-GRNs can effectively coordinate and integrate the heterogeneous information from within constructions.
DOI: 10.18653/v1/d19-1464
发表时间: 2019-09
期刊: ArXiv
影响因子: --
作者:
Chen Zhang;Qiuchi Li;D. Song
通讯作者: Chen Zhang;Qiuchi Li;D. Song
DOI: 10.1016/j.eswa.2021.115712
发表时间: 2021-12
期刊: Expert Syst. Appl.
影响因子: --
作者:
Xiaofei Zhu;Ling Zhu;Jiafeng Guo;Shangsong Liang;S. Dietze
通讯作者: Xiaofei Zhu;Ling Zhu;Jiafeng Guo;Shangsong Liang;S. Dietze
DOI: 10.3115/v1/s14-2036
发表时间: 2014-08
期刊: --
影响因子: --
作者:
Joachim Wagner;Piyush Arora;Santiago Cortés;Utsab Barman;D. Bogdanova;Jennifer Foster;L. Tounsi
通讯作者: Joachim Wagner;Piyush Arora;Santiago Cortés;Utsab Barman;D. Bogdanova;Jennifer Foster;L. Tounsi
DOI: 10.1007/978-981-16-0100-2_8
发表时间: 2021
期刊: Text Data Mining
影响因子: --
作者:
Chengqing Zong;Rui Xia;Jiajun Zhang
通讯作者: Chengqing Zong;Rui Xia;Jiajun Zhang
DOI: 10.1609/aaai.v32i1.12048
发表时间: 2018-04
影响因子: 4.7
作者:
Yukun Ma;Haiyun Peng;E. Cambria
通讯作者: Yukun Ma;Haiyun Peng;E. Cambria