arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.11635cs.CLcs.AIcs.LG
收藏

一种分布式的文本控制生成方法

A Distributional Approach to Controlled Text Generation

Cairo University(开罗大学);Naver Labs Europe(NAVER欧洲实验室)

Muhammad Khalifa, Hady Elsahar, Marc Dymetman

摘要:

我们提出了一个分布式的方法来解决控制文本生成从预先训练的语言模型(LM)。这种方法允许指定,在一个单一的正式框架中,“逐点”和“分布”的约束,在目标LM -据我们所知,第一个模型与这种一般性-同时最大限度地减少KL发散从初始LM分布。最佳的目标分布,然后唯一地确定为一个明确的EBM(基于能量的模型)表示。从该最佳表示,然后我们通过策略梯度的自适应分布变体来训练目标控制的自回归LM。我们进行了第一组实验,逐点约束显示我们的方法的优势,在一组基线,在获得控制LM平衡约束满足与初始LM的发散。然后,我们进行实验的分布约束,我们的方法的一个独特的功能,证明其潜力作为一个补救措施的偏差问题的语言模型。通过消融研究,我们表明我们的自适应技术的有效性,以获得更快的收敛。(Code网址:https://github.com/naver/gdc)

英文摘要:

We propose a Distributional Approach for addressing Controlled Text Generation from pre-trained Language Models (LMs). This approach permits to specify, in a single formal framework, both "pointwise" and "distributional" constraints over the target LM -- to our knowledge, the first model with such generality -- while minimizing KL divergence from the initial LM distribution. The optimal target distribution is then uniquely determined as an explicit EBM (Energy-Based Model) representation. From that optimal representation we then train a target controlled Autoregressive LM through an adaptive distributional variant of Policy Gradient. We conduct a first set of experiments over pointwise constraints showing the advantages of our approach over a set of baselines, in terms of obtaining a controlled LM balancing constraint satisfaction with divergence from the initial LM. We then perform experiments over distributional constraints, a unique feature of our approach, demonstrating its potential as a remedy to the problem of Bias in Language Models. Through an ablation study, we show the effectiveness of our adaptive technique for obtaining faster convergence. (Code available at https://github.com/naver/gdc)

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。

↑