基于神经元分解Oracle的可控文本生成
Controllable Text Generation with Neurally-Decomposed Oracle
摘要:
我们提出了一个通用的和有效的框架来控制自回归生成模型与神经元分解Oracle(NADO)。给定一个预训练的基础语言模型和一个序列级布尔oracle函数,我们建议将oracle函数分解为令牌级指导,以在文本生成中引导基础模型。具体而言,令牌级指导由一个神经模型近似,该神经模型使用从基础模型中采样的示例进行训练,不需要额外的辅助标记数据。基于后验正则化,我们提出了封闭形式的最优解,将令牌级指导纳入可控生成的基础模型。我们进一步提供了一个理论分析NADO的近似质量如何影响可控生成的结果。在两个应用程序上进行的实验:(1)具有词法约束的文本生成和(2)具有形式控制的机器翻译表明,我们的框架有效地引导基础模型向给定的Oracle,同时保持高的生成质量。
英文摘要:
We propose a general and efficient framework to control auto-regressive generation models with NeurAlly-Decomposed Oracle (NADO). Given a pre-trained base language model and a sequence-level boolean oracle function, we propose to decompose the oracle function into token-level guidance to steer the base model in text generation. Specifically, the token-level guidance is approximated by a neural model trained with examples sampled from the base model, demanding no additional auxiliary labeled data. Based on posterior regularization, we present the closed-form optimal solution to incorporate the token-level guidance into the base model for controllable generation. We further provide a theoretical analysis of how the approximation quality of NADO affects the controllable generation results. Experiments conducted on two applications: (1) text generation with lexical constraints and (2) machine translation with formality control demonstrate that our framework efficiently guides the base model towards the given oracle while maintaining high generation quality.
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。