Zero-Shot Learners for Natural Language Understanding via a Unified Multiple-Choice Perspective
Lists
Only you see this
Abstract
Zero-shot learning is an approach where models generalize to unseen tasks without direct training on them. We introduce the Unified Multiple-Choice (UniMC) framework, which is format-independent, compatible with various formats, and applicable to tasks like text classification and sentiment analysis. Furthermore, we design a two-stage tuning method, initially training on multiple-choice formats to develop format-agnostic capabilities, and subsequently enabling direct predictions on unseen tasks for zero-shot learning. Our methodology avoids issues in large-scale models like FLAN, enhancing generalization and reducing parameters. In experiments, UniMC shows State-of-the-Art (SOTA) performance across out-of-domain and in-domain benchmarks, with only 235M parameters, far fewer than previous methods. Moreover, the UniMC-Chinese model excels beyond human performance on benchmarks like EPRSTMT and CHID-FC, underscoring its generalization capacity across languages. Additionally, ablation experiments demonstrate the effectiveness of our design. The code and model weights are available at https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/main/fengshen/examples/unimc.
BibTeX
@inproceedings{wang2023zero,
author = {Junjie Wang and Ping Yang and Ruyi Gan and Yuxiang Zhang and Jiaxing Zhang and Tetsuya Sakai},
title = {{Zero-Shot Learners for Natural Language Understanding via a Unified Multiple-Choice Perspective}},
booktitle = {IEEE Access},
year = {2023},
url = {https://openreview.net/forum?id=MNTwwmjdxg},
}Loading related content...