Abstract
Unsupervised constrained text generation aims to generate text under a given set of constraints without any supervised data. Current state-of-the-art methods stochastically sample edit positions and actions, which may cause unnecessary search steps. In this paper, we propose PMCTG to improve effectiveness by searching for the best edit position and action in each step. Specifically, PMCTG extends perturbed masking technique to effectively search for the most incongruent token to edit. Then it introduces four multi-aspect scoring functions to select edit action to further reduce search difficulty. Since PMCTG does not require supervised data, it could be applied to different generation tasks. We show that under the unsupervised setting, PMCTG achieves new state-of-the-art results in two representative tasks, namely keywords-to-sentence generation and paraphrasing.
Abstract (translated)
无监督约束文本生成旨在生成满足给定约束条件的文本,而无需任何有监督数据。目前最先进的方法随机采样编辑位置和动作,这可能导致不必要的搜索步骤。在本文中,我们提出PMCTG来提高效果,通过在每一步中寻找最佳编辑位置和动作。具体来说,PMCTG扩展了扰动掩码技术,以有效搜索最不和谐的词。然后它引入了四个多方面评分函数,以选择编辑动作进一步减少搜索难度。由于PMCTG不需要有监督数据,因此可以应用于不同的生成任务。我们证明了在无监督设置下,PMCTG在两个具有代表性的任务(即关键词到句子生成和的同义词)上实现了与当前最佳方法相同的最新的最佳结果。
URL
https://arxiv.org/abs/2404.15877