An Enhanced Knowledge Injection Model for Commonsense Generation

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 <PRE_TAG>scaling module</POST_TAG>, into the pretrained <PRE_TAG>encoder-decoder model</POST_TAG> for <PRE_TAG>prototype modeling</POST_TAG> to enhance the <PRE_TAG>knowledge injection procedure</POST_TAG>. We conduct experiment on CommonGen benchmark, and experimental results show that our method significantly improves the performance on all the metrics.