FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark

TL;DR

This paper introduces FewCLUE, a comprehensive benchmark for evaluating few-shot learning methods on Chinese NLP tasks, providing insights into method effectiveness and a platform for future research progress.

Contribution

It presents the first extensive Chinese few-shot learning benchmark, evaluates multiple methods, and offers tools and a leaderboard to advance Chinese NLP research.

Findings

Performance of few-shot methods varies with pre-trained models.

PET and P-tuning outperform others with specific models.

Benchmark facilitates fair comparison and future research.

Abstract

Pretrained Language Models (PLMs) have achieved tremendous success in natural language understanding tasks. While different learning schemes -- fine-tuning, zero-shot, and few-shot learning -- have been widely explored and compared for languages such as English, there is comparatively little work in Chinese to fairly and comprehensively evaluate and compare these methods and thus hinders cumulative progress. In this paper, we introduce the Chinese Few-shot Learning Evaluation Benchmark (FewCLUE), the first comprehensive few-shot evaluation benchmark in Chinese. It includes nine tasks, ranging from single-sentence and sentence-pair classification tasks to machine reading comprehension tasks. We systematically evaluate five state-of-the-art (SOTA) few-shot learning methods (including PET, ADAPET, LM-BFF, P-tuning and EFL), and compare their performance with fine-tuning and zero-shot learning schemes on the newly constructed FewCLUE benchmark. Experimental results reveal that: 1) The effect of different few-shot learning methods is sensitive to the pre-trained model to which the methods are applied; 2) PET and P-tuning achieve the best overall performance with RoBERTa and ERNIE respectively. Our benchmark is used in the few-shot learning contest of NLPCC 2021. In addition, we provide a user-friendly toolkit, as well as an online leaderboard to help facilitate further progress on Chinese few-shot learning. We provide a baseline performance on different learning methods, a reference for future research.