Adam-Smith at SemEval-2023 Task 4: Discovering Human Values in Arguments with Ensembles of Transformer-based Models

Daniel Schroter, D. Dementieva, G. Groh
{"title":"Adam-Smith at SemEval-2023 Task 4: Discovering Human Values in Arguments with Ensembles of Transformer-based Models","authors":"Daniel Schroter, D. Dementieva, G. Groh","doi":"10.48550/arXiv.2305.08625","DOIUrl":null,"url":null,"abstract":"This paper presents the best-performing approach alias “Adam Smith” for the SemEval-2023 Task 4: “Identification of Human Values behind Arguments”. The goal of the task was to create systems that automatically identify the values within textual arguments. We train transformer-based models until they reach their loss minimum or f1-score maximum. Ensembling the models by selecting one global decision threshold that maximizes the f1-score leads to the best-performing system in the competition. Ensembling based on stacking with logistic regressions shows the best performance on an additional dataset provided to evaluate the robustness (“Nahj al-Balagha”). Apart from outlining the submitted system, we demonstrate that the use of the large ensemble model is not necessary and that the system size can be significantly reduced.","PeriodicalId":444285,"journal":{"name":"International Workshop on Semantic Evaluation","volume":"88 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Workshop on Semantic Evaluation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2305.08625","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

This paper presents the best-performing approach alias “Adam Smith” for the SemEval-2023 Task 4: “Identification of Human Values behind Arguments”. The goal of the task was to create systems that automatically identify the values within textual arguments. We train transformer-based models until they reach their loss minimum or f1-score maximum. Ensembling the models by selecting one global decision threshold that maximizes the f1-score leads to the best-performing system in the competition. Ensembling based on stacking with logistic regressions shows the best performance on an additional dataset provided to evaluate the robustness (“Nahj al-Balagha”). Apart from outlining the submitted system, we demonstrate that the use of the large ensemble model is not necessary and that the system size can be significantly reduced.
Adam-Smith在SemEval-2023的任务4:在基于变压器的模型集合的争论中发现人类的价值
本文为SemEval-2023任务4:“识别争论背后的人类价值”提出了性能最好的方法,别名为“亚当·斯密”。该任务的目标是创建能够自动识别文本参数中的值的系统。我们训练基于变压器的模型,直到它们达到损耗最小值或f1分数最大值。通过选择一个使f1得分最大化的全局决策阈值来集成模型,可以使系统在竞争中表现最佳。基于逻辑回归叠加的集成在额外的数据集上显示出最佳性能,以评估鲁棒性(“Nahj al-Balagha”)。除了概述所提交的系统外,我们还证明了没有必要使用大型集成模型,并且可以显着减小系统大小。
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
自引率
0.00%
发文量
0
×
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