An Enhanced Knowledge Injection Model for Commonsense Generation

Autor:	Fan, Zhihao, Gong, Yeyun, Wei, Zhongyu, Wang, Siyuan, Huang, Yameng, Jiao, Jian, Huang, Xuanjing, Duan, Nan, Zhang, Ruofei
Rok vydání:	2020
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted to COLING 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2012.00366 Zobrazit plný text záznamu View this record from Arxiv