论文标题
通过密度比估计来改善文本生成的最大似然训练
Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation
论文作者
论文摘要
在实际有限的样本场景中，经过最大似然估计训练的自动回归序列生成模型会遭受暴露偏差问题。关键是最大似然估计的训练样本的数量通常受到限制，并且在训练和推理阶段的输入数据分布也有所不同。提出了许多方法来解决上述问题（Yu等，2017; Lu等，2018），该方法依赖于非平稳模型分布的抽样，并且具有较高的差异或有偏见的估计。在本文中，我们提出了一种针对自动回归序列生成模型的新培训方案，当在文本生成中遇到的大型样本空间中运行时，它是有效且稳定的。我们从自我实践的新角度得出算法，并通过密度比估计引入偏差校正。关于综合数据和现实世界文本生成任务的广泛实验结果表明，就质量和多样性而言，我们的方法稳定优于最大似然估计和其他最新序列生成模型。
Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios. The crux is that the number of training samples for Maximum Likelihood Estimation is usually limited and the input data distributions are different at training and inference stages. Many method shave been proposed to solve the above problem (Yu et al., 2017; Lu et al., 2018), which relies on sampling from the non-stationary model distribution and suffers from high variance or biased estimations. In this paper, we proposeψ-MLE, a new training scheme for auto-regressive sequence generative models, which is effective and stable when operating at large sample space encountered in text generation. We derive our algorithm from a new perspective of self-augmentation and introduce bias correction with density ratio estimation. Extensive experimental results on synthetic data and real-world text generation tasks demonstrate that our method stably outperforms Maximum Likelihood Estimation and other state-of-the-art sequence generative models in terms of both quality and diversity.
