少注释，多分类:用深度迁移学习和BERT-NLI解决监督机器学习的数据稀缺问题

IF 4.7 2区社会学 Q1 POLITICAL SCIENCE Political Analysis Pub Date : 2023-06-09 DOI:10.1017/pan.2023.20

Moritz Laurer, Wouter van Atteveldt, Andreu Casas, Kasper Welbers

引用次数: 28

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Less Annotating, More Classifying: Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT-NLI

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

Political Analysis POLITICAL SCIENCE-

CiteScore

8.80

自引率

3.70%

发文量

期刊介绍： Political Analysis chronicles these exciting developments by publishing the most sophisticated scholarship in the field. It is the place to learn new methods, to find some of the best empirical scholarship, and to publish your best research.

期刊最新文献

Synthetic Replacements for Human Survey Data? The Perils of Large Language Models NonRandom Tweet Mortality and Data Access Restrictions: Compromising the Replication of Sensitive Twitter Studies Generalizing toward Nonrespondents: Effect Estimates in Survey Experiments Are Broadly Similar for Eager and Reluctant Participants Estimators for Topic-Sampling Designs Flexible Estimation of Policy Preferences for Witnesses in Committee Hearings