CLUR: Uncertainty Estimation for Few-Shot Text Classification with Contrastive Learning
| dc.contributor.author | He, Jianfeng | en |
| dc.contributor.author | Zhang, Xuchao | en |
| dc.contributor.author | Lei, Shuo | en |
| dc.contributor.author | Alhamadani, Abdulaziz | en |
| dc.contributor.author | Chen, Fanglan | en |
| dc.contributor.author | Xiao, Bei | en |
| dc.contributor.author | Lu, Chang-Tien | en |
| dc.date.accessioned | 2023-09-05T13:39:03Z | en |
| dc.date.available | 2023-09-05T13:39:03Z | en |
| dc.date.issued | 2023-08-06 | en |
| dc.date.updated | 2023-09-01T07:49:32Z | en |
| dc.description.abstract | Few-shot text classification has extensive application where the sample collection is expensive or complicated. When the penalty for classification errors is high, such as early threat event detection with scarce data, we expect to know “whether we should trust the classification results or reexamine them.” This paper investigates the Uncertainty Estimation for Few-shot Text Classification (UEFTC), an unexplored research area. Given limited samples, a UEFTC model predicts an uncertainty score for a classification result, which is the likelihood that the classification result is false. However, many traditional uncertainty estimation models in text classification are unsuitable for implementing a UEFTC model. These models require numerous training samples, whereas the few-shot setting in UEFTC only provides a few or just one support sample for each class in an episode. We propose Contrastive Learning from Uncertainty Relations (CLUR) to address UEFTC. CLUR can be trained with only one support sample for each class with the help of pseudo uncertainty scores. Unlike previous works that manually set the pseudo uncertainty scores, CLUR self-adaptively learns them using our proposed uncertainty relations. Specifically, we explore four model structures in CLUR to investigate the performance of three common-used contrastive learning components in UEFTC and find that two of the components are effective. Experiment results prove that CLUR outperforms six baselines on four datasets, including an improvement of 4.52% AUPR on an RCV1 dataset in a 5-way 1-shot setting. Our code and data split for UEFTC are in https: //github.com/he159ok/CLUR_UncertaintyEst_FewShot_TextCls. | en |
| dc.description.version | Published version | en |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.doi | https://doi.org/10.1145/3580305.3599276 | en |
| dc.identifier.uri | http://hdl.handle.net/10919/116204 | en |
| dc.language.iso | en | en |
| dc.publisher | ACM | en |
| dc.rights | Creative Commons Attribution 4.0 International | en |
| dc.rights.holder | The author(s) | en |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | en |
| dc.title | CLUR: Uncertainty Estimation for Few-Shot Text Classification with Contrastive Learning | en |
| dc.type | Article - Refereed | en |
| dc.type.dcmitype | Text | en |