文本回归预训练模型的不确定性估计与减少

IF 4.2 1区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Transactions of the Association for Computational Linguistics Pub Date : 2022-06-01 DOI:10.1162/tacl_a_00483
Yuxia Wang, Daniel Beck, Timothy Baldwin, K. Verspoor
{"title":"文本回归预训练模型的不确定性估计与减少","authors":"Yuxia Wang, Daniel Beck, Timothy Baldwin, K. Verspoor","doi":"10.1162/tacl_a_00483","DOIUrl":null,"url":null,"abstract":"Abstract State-of-the-art classification and regression models are often not well calibrated, and cannot reliably provide uncertainty estimates, limiting their utility in safety-critical applications such as clinical decision-making. While recent work has focused on calibration of classifiers, there is almost no work in NLP on calibration in a regression setting. In this paper, we quantify the calibration of pre- trained language models for text regression, both intrinsically and extrinsically. We further apply uncertainty estimates to augment training data in low-resource domains. Our experiments on three regression tasks in both self-training and active-learning settings show that uncertainty estimation can be used to increase overall performance and enhance model generalization.","PeriodicalId":33559,"journal":{"name":"Transactions of the Association for Computational Linguistics","volume":"10 1","pages":"680-696"},"PeriodicalIF":4.2000,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":"{\"title\":\"Uncertainty Estimation and Reduction of Pre-trained Models for Text Regression\",\"authors\":\"Yuxia Wang, Daniel Beck, Timothy Baldwin, K. Verspoor\",\"doi\":\"10.1162/tacl_a_00483\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract State-of-the-art classification and regression models are often not well calibrated, and cannot reliably provide uncertainty estimates, limiting their utility in safety-critical applications such as clinical decision-making. While recent work has focused on calibration of classifiers, there is almost no work in NLP on calibration in a regression setting. In this paper, we quantify the calibration of pre- trained language models for text regression, both intrinsically and extrinsically. We further apply uncertainty estimates to augment training data in low-resource domains. Our experiments on three regression tasks in both self-training and active-learning settings show that uncertainty estimation can be used to increase overall performance and enhance model generalization.\",\"PeriodicalId\":33559,\"journal\":{\"name\":\"Transactions of the Association for Computational Linguistics\",\"volume\":\"10 1\",\"pages\":\"680-696\"},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2022-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"13\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Transactions of the Association for Computational Linguistics\",\"FirstCategoryId\":\"98\",\"ListUrlMain\":\"https://doi.org/10.1162/tacl_a_00483\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transactions of the Association for Computational Linguistics","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1162/tacl_a_00483","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 13

摘要

目前最先进的分类和回归模型往往没有很好地校准,不能可靠地提供不确定性估计,限制了它们在临床决策等安全关键应用中的效用。虽然最近的工作主要集中在分类器的校准上,但在回归设置中几乎没有关于NLP校准的工作。在本文中,我们量化了文本回归的预训练语言模型的校准,包括内在的和外在的。我们进一步应用不确定性估计来增加低资源领域的训练数据。我们在自我训练和主动学习设置下的三个回归任务上的实验表明,不确定性估计可以用来提高整体性能和增强模型泛化。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Uncertainty Estimation and Reduction of Pre-trained Models for Text Regression
Abstract State-of-the-art classification and regression models are often not well calibrated, and cannot reliably provide uncertainty estimates, limiting their utility in safety-critical applications such as clinical decision-making. While recent work has focused on calibration of classifiers, there is almost no work in NLP on calibration in a regression setting. In this paper, we quantify the calibration of pre- trained language models for text regression, both intrinsically and extrinsically. We further apply uncertainty estimates to augment training data in low-resource domains. Our experiments on three regression tasks in both self-training and active-learning settings show that uncertainty estimation can be used to increase overall performance and enhance model generalization.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
32.60
自引率
4.60%
发文量
58
审稿时长
8 weeks
期刊介绍: The highly regarded quarterly journal Computational Linguistics has a companion journal called Transactions of the Association for Computational Linguistics. This open access journal publishes articles in all areas of natural language processing and is an important resource for academic and industry computational linguists, natural language processing experts, artificial intelligence and machine learning investigators, cognitive scientists, speech specialists, as well as linguists and philosophers. The journal disseminates work of vital relevance to these professionals on an annual basis.
期刊最新文献
General then Personal: Decoupling and Pre-training for Personalized Headline Generation MissModal: Increasing Robustness to Missing Modality in Multimodal Sentiment Analysis Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training Learning More from Mixed Emotions: A Label Refinement Method for Emotion Recognition in Conversations An Efficient Self-Supervised Cross-View Training For Sentence Embedding
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1