论文标题
神经成分：学会从多种模型中生成
Neural Composition: Learning to Generate from Multiple Models
论文作者
论文摘要
将模型分解为多个组件在许多应用程序（例如语言建模（LM））中至关重要，因为它可以分别调整单个组件，并使某些组件偏向用户的个人喜好。传统上，语言模型的上下文和个性化适应性是通过基于班级的分解来实现的，该分解需要班级的数据，或通过偏向于规模限制的单个短语。在本文中，我们提出了一个结合模型定义组件的系统，通过学习何时从每个组件中激活生成过程，以及如何直接通过未标记的文本数据组合每个组件的概率分布。
Decomposing models into multiple components is critically important in many applications such as language modeling (LM) as it enables adapting individual components separately and biasing of some components to the user's personal preferences. Conventionally, contextual and personalized adaptation for language models, are achieved through class-based factorization, which requires class-annotated data, or through biasing to individual phrases which is limited in scale. In this paper, we propose a system that combines model-defined components, by learning when to activate the generation process from each individual component, and how to combine probability distributions from each component, directly from unlabeled text data.
