arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.04044cs.CL
收藏

Diffusion-NAT:用于非自回归文本生成的自我提示离散扩散

Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation

Renmin University of China(中国人民大学)

Kun Zhou, Yifan Li, Wayne Xin Zhao, Ji-Rong Wen

AI总结:

Diffusion-NAT将离散扩散模型与BART结合,通过统一去噪和掩码恢复任务及迭代自我提示,在7个数据集上超越非自回归和自回归文本生成方法。

摘要:

最近,连续扩散模型(CDM)已被引入非自回归(NAR)文本到文本生成中。然而,文本的离散性质增加了CDM生成连贯流畅文本的难度,也导致了CDM与先进NLP技术(尤其是流行的预训练语言模型(PLMs))之间的不兼容问题。为解决这一问题,我们提出了Diffusion-NAT,它将离散扩散模型(DDM)引入NAR文本到文本生成,并集成BART以提升性能。通过修改BART的解码过程和DDM的典型设置,我们将BART的推理过程与DDM的去噪过程统一到相同的NAR掩码标记恢复任务中。这样,DDM可以依赖BART进行去噪,从而同时受益于BART丰富的预训练知识和DDM的迭代细化范式。此外,我们还提出了迭代自我提示策略以进一步提高生成质量。在7个数据集上的实验结果表明,我们的方法能够优于竞争性的NAR方法,甚至超越自回归方法。我们的代码和数据将公开发布。

英文摘要:

Recently, continuous diffusion models (CDM) have been introduced into non-autoregressive (NAR) text-to-text generation. However, the discrete nature of text increases the difficulty of CDM to generate coherent and fluent texts, and also causes the incompatibility problem between CDM and advanced NLP techniques, especially the popular pre-trained language models~(PLMs). To solve it, we propose Diffusion-NAT, which introduces discrete diffusion models~(DDM) into NAR text-to-text generation and integrates BART to improve the performance. By revising the decoding process of BART and the typical settings of DDM, we unify the inference process of BART and the denoising process of DDM into the same NAR masked tokens recovering task. In this way, DDM can rely on BART to perform denoising, which can benefit from both the rich pre-learned knowledge of BART and the iterative refining paradigm of DDM. Besides, we also propose the iterative self-prompting strategy to further improve the generation quality. Experimental results on 7 datasets show that our approach can outperform competitive NAR methods, and even surpass autoregressive methods. Our code and data will be publicly released.

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。

↑