ACL 2021short13 citations
Distinct Label Representations for Few-Shot Text Classification
Sora Ohashi, Junya Takayama, Tomoyuki Kajiwara, Yuki Arase
Abstract
Few-shot text classification aims to classify inputs whose label has only a few examples. Previous studies overlooked the semantic relevance between label representations. Therefore, they are easily confused by labels that are relevant. To address this problem, we propose a method that generates distinct label representations that embed information specific to each label. Our method is applicable to conventional few-shot classification models. Experimental results show that our method significantly improved the performance of few-shot text classification across models and datasets.
BibTeX
@inproceedings{ohashi-etal-2021-distinct,
title = "Distinct Label Representations for Few-Shot Text Classification",
author = "Ohashi, Sora and
Takayama, Junya and
Kajiwara, Tomoyuki and
Arase, Yuki",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.105/",
doi = "10.18653/v1/2021.acl-short.105",
pages = "831--836"
}