Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of the output. In this work, we propose to ameliorate this cost by using an Imitation Learning approach to explore the level of diversity that a language generation model can reliably produce. Specifically, we augment the decoding process with a meta-classifier trained to distinguish which words at any given timestep will lead to high-quality output. We focus our experiments on concept-to-text generation where models are sensitive to the inclusion of irrelevant words due to the strict relation between input and output. Our analysis shows that previous methods for diversity underperform in this setting, while human evaluation suggests that our proposed method achieves a high level of diversity with minimal effect to the output's fluency and adequacy.
翻译:语言生成任务的深层次学习模式往往会产生重复产出。 已经提出各种方法鼓励在解码过程中的字典多样性,但这往往以产出的流畅和充分性为代价。 在这项工作中,我们提议通过使用模拟学习方法来提高这一成本,以探索语言生成模式能够可靠地产生的多样性水平。 具体地说,我们用一个经过培训的元分类器来强化解码进程,以区分在任何特定时间步骤中哪些词将导致高质量的产出。 我们把实验重点放在概念到文字生成上,因为由于输入和产出之间的严格关系,模型对纳入无关的字句十分敏感。 我们的分析表明,以前关于多样性的方法在此环境中表现不佳,而人类评价则表明,我们拟议的方法实现了高度的多样性,对产出的流畅和充分性影响最小。