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 2201.08670cs.CL
收藏

Context-Tuning:学习用于自然语言生成的上下文化语句

Context-Tuning: Learning Contextualized Prompts for Natural Language Generation

Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Université de Montréal(蒙特利尔大学);School of Information, Renmin University of China(中国人民大学信息学院);Beijing Academy of Artificial Intelligence(北京智源人工智能研究院)

Tianyi Tang, Junyi Li, Wayne Xin Zhao, Ji-Rong Wen

摘要:

最近,预训练语言模型(PLM)在语言生成方面取得了巨大的成功。为了利用PLM编码的丰富知识,一个简单而强大的范例是使用离散令牌或连续嵌入形式的提示。在现有的研究中,这些提示方法通常与输入无关,缺乏对输入语义的充分考虑。为了解决这个问题,我们提出了一种新的连续提示的方法,称为上下文调整,微调PLM的自然语言生成。首先,根据输入文本导出提示,以从PLM中提取有用的知识用于生成。我们把这种提示称为语境化提示。其次,我们使用连续的逆提示,以改善自然语言的生成过程,通过建模从输出到输入的逆生成过程,使生成的文本更相关的输入。此外,我们利用一个轻量级的上下文调整方法,微调只有0.12%的参数,同时保持良好的性能。我们的代码可在https://github.com/RUCAIBox/Context-Tuning上公开获取。

英文摘要:

Recently, pretrained language models (PLMs) have had exceptional success in language generation. To leverage the rich knowledge encoded by PLMs, a simple yet powerful paradigm is to use prompts in the form of either discrete tokens or continuous embeddings. In existing studies, these prompting methods are typically independent of the inputs, lacking sufficient consideration of input semantics. To address this issue, we propose a novel continuous prompting approach, called context-tuning, to fine-tuning PLMs for natural language generation. Firstly, the prompts are derived based on the input text to elicit useful knowledge from PLMs for generation. We refer to such prompts as contextualized prompts. Secondly, we use continuous inverse prompting to improve the process of natural language generation by modeling an inverse generation process from output to input, making the generated text more relevant to the inputs. Furthermore, we utilize a lightweight context-tuning method that fine-tunes only 0.12% of the parameters while maintaining good performance. Our code is publicly available at https://github.com/RUCAIBox/Context-Tuning.

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。

↑