arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.10593cs.CLcs.AI
收藏

基于PDD的Few-Shot自然语言推理生成:即时动态演示

Few-Shot Natural Language Inference Generation with PDD: Prompt and Dynamic Demonstration

Shanghai Jiao Tong University(上海交通大学)

Kaijian Li, Shansan Gong, Kenny Q. Zhu

摘要:

自然语言推理生成任务是在给定文本前提和两者之间的逻辑关系的情况下生成文本假设。该任务可用于实际的数据增强和可控文本生成。在本文中,我们提出了语言模型与提示和动态演示(LM-PDD)来解决这个问题,在Few-Shot设置。该框架在资源较少的情况下优于标准的微调模型,在SNLI和MNLI数据集上取得了平均8%的绝对改进,在13个自然语言分类任务上的结果也表明,该动态演示方法具有良好的泛化能力。

英文摘要:

Natural Language Inference Generation task is to generate a text hypothesis given a text premise and a logical relation between the two. This task can be used in data augmentation and controllable text generation in practice. In this paper, we propose language models with prompt and dynamic demonstration (LM-PDD) to tackle this problem in few-shot settings. Our framework outperforms standard fine-tuned models with low resource, achieving an average 8% absolute improvement on SNLI and MNLI datasets, and the results on 13 natural language classification tasks also show that our dynamic demonstration method has good generalizability.

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。

↑