arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.00902cs.CL
收藏

机器人是否使用自然语言解决NLP任务?

Do Prompts Solve NLP Tasks Using Natural Language?

Westlake University(西湖大学);University of Electronic Science and Technology of China(电子科技大学);Zhejiang University(浙江大学);Westlake Institute for Advanced Study(西湖高等研究院)

Sen Yang, Yunchen Zhang, Leyang Cui, Yue Zhang

摘要:

由于大型预训练语言模型的先进改进,基于语义的微调被证明对各种下游任务是有效的。虽然已经研究了许多提示方法,但是仍然不知道在三种类型的提示(即,人工设计的提示、模式提示和空提示)。在这项工作中,我们经验比较了三种类型的提示下,Few-Shot和完全监督的设置。我们的实验结果表明,图式提示是最有效的一般。此外,当训练数据的规模变大时,性能差距趋于减小。

英文摘要:

Thanks to the advanced improvement of large pre-trained language models, prompt-based fine-tuning is shown to be effective on a variety of downstream tasks. Though many prompting methods have been investigated, it remains unknown which type of prompts are the most effective among three types of prompts (i.e., human-designed prompts, schema prompts and null prompts). In this work, we empirically compare the three types of prompts under both few-shot and fully-supervised settings. Our experimental results show that schema prompts are the most effective in general. Besides, the performance gaps tend to diminish when the scale of training data grows large.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑