EdiText:基于扩散语言模型的可控由粗到细文本编辑
EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
AI总结:
本文提出 EdiText,结合 SDEdit 与自条件化细粒度编辑方法,实现由粗到细的可控文本编辑,在毒性与情感控制等任务中展现出广泛且精确的属性调整能力。
摘要:
我们提出 EdiText,一种可控文本编辑方法,可在不同尺度上将参考文本修改为所需属性。我们整合了一种基于 SDEdit 的编辑技术,允许对文本编辑程度进行广泛调整。此外,我们引入了一种基于自条件化的新颖细粒度编辑方法,可对参考文本进行精细控制。该细粒度方法在能够独立进行编辑的同时,与 SDEdit 方法集成后,使 EdiText 能够在期望范围内进行精确调整。EdiText 展示了其可控性,能够在包括毒性控制和情感控制在内的各种任务中,在广泛的级别范围内稳健地调整参考文本。
英文摘要:
We propose EdiText, a controllable text editing method that modifies the reference text to desired attributes at various scales. We integrate an SDEdit-based editing technique that allows for broad adjustments in the degree of text editing. Additionally, we introduce a novel fine-level editing method based on self-conditioning, which allows subtle control of reference text. While being capable of editing on its own, this fine-grained method, integrated with the SDEdit approach, enables EdiText to make precise adjustments within the desired range. EdiText demonstrates its controllability to robustly adjust reference text at a broad range of levels across various tasks, including toxicity control and sentiment control.
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。