论文标题
增强的常识性知识注入模型
An Enhanced Knowledge Injection Model for Commonsense Generation
论文作者
论文摘要
常识生成旨在基于一组提供的概念生成合理的日常场景描述。从头开始挖掘概念的关系是非平凡的，因此，我们从外部知识中检索原型，以帮助对场景的理解以更好地描述生成。我们将两个其他模块（即位置指标和缩放模块）集成到预验证的编码模型中，以增强知识注入程序的原型建模。我们对公共基准进行实验，实验结果表明，我们的方法显着提高了所有指标的性能。
Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts. Digging the relationship of concepts from scratch is non-trivial, therefore, we retrieve prototypes from external knowledge to assist the understanding of the scenario for better description generation. We integrate two additional modules, namely position indicator and scaling module, into the pretrained encoder-decoder model for prototype modeling to enhance the knowledge injection procedure. We conduct experiment on CommonGen benchmark, and experimental results show that our method significantly improves the performance on all the metrics.
