一个简单的半监督联合学习框架,用于少量文本分类

Shaoshuai Lu, Long Chen, Wenjing Wang, Cai Xu, Wei Zhao, Ziyu Guan, Guangyue Lu
{"title":"一个简单的半监督联合学习框架,用于少量文本分类","authors":"Shaoshuai Lu, Long Chen, Wenjing Wang, Cai Xu, Wei Zhao, Ziyu Guan, Guangyue Lu","doi":"10.1145/3573942.3573945","DOIUrl":null,"url":null,"abstract":"The lack of labeled data is the bottleneck restricting deep text classification algorithm. State-of-the-art for most existing deep text classification methods follow the two-step transfer learning paradigm: pre-training a large model on an auxiliary task, and then fine-tuning the model on a labeled data. Their shortcoming is the high cost of training. To reduce training costs as well as alleviate the need for labeled data, we present a novel simple Semi-Supervised Joint Learning (SSJL) framework for few-shot text classification that captures the rich text semantics from large user-tagged data (referred to as weakly-labeled data) with noisy labels while also learning correct category distributions in small labeled data. We refine the contrastive loss function to better exploit inter-class contrastive patterns, making contrastive learning more applicable to the weakly-labeled setting. Besides, an appropriate temperature hyper-parameter can improve model robustness under label noise. The experimental results on four real-world datasets show that our approach outperforms the other baseline methods. Moreover, SSJL significantly boosts the deep models’ performance with only 0.5% (i.e. 32 samples) of the labeled data, showing its robustness in the data sparsity scenario.","PeriodicalId":103293,"journal":{"name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","volume":"114 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Simple Semi-Supervised Joint Learning Framework for Few-shot Text Classification\",\"authors\":\"Shaoshuai Lu, Long Chen, Wenjing Wang, Cai Xu, Wei Zhao, Ziyu Guan, Guangyue Lu\",\"doi\":\"10.1145/3573942.3573945\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The lack of labeled data is the bottleneck restricting deep text classification algorithm. State-of-the-art for most existing deep text classification methods follow the two-step transfer learning paradigm: pre-training a large model on an auxiliary task, and then fine-tuning the model on a labeled data. Their shortcoming is the high cost of training. To reduce training costs as well as alleviate the need for labeled data, we present a novel simple Semi-Supervised Joint Learning (SSJL) framework for few-shot text classification that captures the rich text semantics from large user-tagged data (referred to as weakly-labeled data) with noisy labels while also learning correct category distributions in small labeled data. We refine the contrastive loss function to better exploit inter-class contrastive patterns, making contrastive learning more applicable to the weakly-labeled setting. Besides, an appropriate temperature hyper-parameter can improve model robustness under label noise. The experimental results on four real-world datasets show that our approach outperforms the other baseline methods. Moreover, SSJL significantly boosts the deep models’ performance with only 0.5% (i.e. 32 samples) of the labeled data, showing its robustness in the data sparsity scenario.\",\"PeriodicalId\":103293,\"journal\":{\"name\":\"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition\",\"volume\":\"114 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3573942.3573945\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3573942.3573945","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

缺乏标记数据是制约深度文本分类算法的瓶颈。大多数现有的深度文本分类方法都遵循两步迁移学习范式:在辅助任务上预训练一个大模型,然后在标记数据上对模型进行微调。他们的缺点是培训费用高。为了降低训练成本并减轻对标记数据的需求,我们提出了一种新的简单的半监督联合学习(SSJL)框架,用于少量文本分类,该框架可以从带有噪声标签的大型用户标记数据(称为弱标记数据)中捕获富文本语义,同时还可以在小标记数据中学习正确的类别分布。我们改进了对比损失函数,以更好地利用类间对比模式,使对比学习更适用于弱标记设置。此外,适当的温度超参数可以提高模型在标签噪声下的鲁棒性。在四个真实数据集上的实验结果表明,我们的方法优于其他基线方法。此外,SSJL仅使用标记数据的0.5%(即32个样本)就显著提升了深度模型的性能,显示了其在数据稀疏场景下的鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Simple Semi-Supervised Joint Learning Framework for Few-shot Text Classification
The lack of labeled data is the bottleneck restricting deep text classification algorithm. State-of-the-art for most existing deep text classification methods follow the two-step transfer learning paradigm: pre-training a large model on an auxiliary task, and then fine-tuning the model on a labeled data. Their shortcoming is the high cost of training. To reduce training costs as well as alleviate the need for labeled data, we present a novel simple Semi-Supervised Joint Learning (SSJL) framework for few-shot text classification that captures the rich text semantics from large user-tagged data (referred to as weakly-labeled data) with noisy labels while also learning correct category distributions in small labeled data. We refine the contrastive loss function to better exploit inter-class contrastive patterns, making contrastive learning more applicable to the weakly-labeled setting. Besides, an appropriate temperature hyper-parameter can improve model robustness under label noise. The experimental results on four real-world datasets show that our approach outperforms the other baseline methods. Moreover, SSJL significantly boosts the deep models’ performance with only 0.5% (i.e. 32 samples) of the labeled data, showing its robustness in the data sparsity scenario.
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
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