Incorporating Multiple Knowledge Sources for Targeted Aspect-based Financial Sentiment Analysis

IF 2.5 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS
Kelvin Du, Frank Xing, E. Cambria
{"title":"Incorporating Multiple Knowledge Sources for Targeted Aspect-based Financial Sentiment Analysis","authors":"Kelvin Du, Frank Xing, E. Cambria","doi":"10.1145/3580480","DOIUrl":null,"url":null,"abstract":"Combining symbolic and subsymbolic methods has become a promising strategy as research tasks in AI grow increasingly complicated and require higher levels of understanding. Targeted Aspect-based Financial Sentiment Analysis (TABFSA) is an example of such complicated tasks, as it involves processes like information extraction, information specification, and domain adaptation. However, little is known about the design principles of such hybrid models leveraging external lexical knowledge. To fill this gap, we define anterior, parallel, and posterior knowledge integration and propose incorporating multiple lexical knowledge sources strategically into the fine-tuning process of pre-trained transformer models for TABFSA. Experiments on the Financial Opinion mining and Question Answering challenge (FiQA) Task 1 and SemEval 2017 Task 5 datasets show that the knowledge-enabled models systematically improve upon their plain deep learning counterparts, and some outperform state-of-the-art results reported in terms of aspect sentiment analysis error. We discover that parallel knowledge integration is the most effective and domain-specific lexical knowledge is more important according to our ablation analysis.","PeriodicalId":45274,"journal":{"name":"ACM Transactions on Management Information Systems","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2023-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Management Information Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3580480","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 8

Abstract

Combining symbolic and subsymbolic methods has become a promising strategy as research tasks in AI grow increasingly complicated and require higher levels of understanding. Targeted Aspect-based Financial Sentiment Analysis (TABFSA) is an example of such complicated tasks, as it involves processes like information extraction, information specification, and domain adaptation. However, little is known about the design principles of such hybrid models leveraging external lexical knowledge. To fill this gap, we define anterior, parallel, and posterior knowledge integration and propose incorporating multiple lexical knowledge sources strategically into the fine-tuning process of pre-trained transformer models for TABFSA. Experiments on the Financial Opinion mining and Question Answering challenge (FiQA) Task 1 and SemEval 2017 Task 5 datasets show that the knowledge-enabled models systematically improve upon their plain deep learning counterparts, and some outperform state-of-the-art results reported in terms of aspect sentiment analysis error. We discover that parallel knowledge integration is the most effective and domain-specific lexical knowledge is more important according to our ablation analysis.
结合多个知识来源进行针对性的面向方面的金融情绪分析
随着人工智能研究任务越来越复杂,对理解水平的要求越来越高,将符号和子符号方法相结合已成为一种很有前途的策略。基于目标方面的金融情绪分析(TABFSA)就是这种复杂任务的一个例子,因为它涉及信息提取、信息规范和领域自适应等过程。然而,人们对利用外部词汇知识的这种混合模型的设计原理知之甚少。为了填补这一空白,我们定义了前向、平行和后向知识整合,并建议将多个词汇知识源战略性地纳入TABFSA的预训练转换模型的微调过程中。在金融意见挖掘和问答挑战(FiQA)任务1和SemEval 2017任务5数据集上的实验表明,基于知识的模型系统地改进了其简单的深度学习模型,并且在方面情绪分析误差方面,一些模型优于最先进的结果。根据我们的消融分析,我们发现平行知识整合是最有效的,而特定领域的词汇知识更为重要。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
ACM Transactions on Management Information Systems
ACM Transactions on Management Information Systems COMPUTER SCIENCE, INFORMATION SYSTEMS-
CiteScore
6.30
自引率
20.00%
发文量
60
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信