论文标题
Transomcs：从语言图到常识性知识
TransOMCS: From Linguistic Graphs to Commonsense Knowledge
论文作者
论文摘要
常识知识获取是人工智能的关键问题。获取常识性知识的常规方法通常需要费力且昂贵的人类注释，这在大规模上是不可行的。在本文中，我们探讨了一种从语言图中挖掘常识性知识的实用方法，其目的是将以语言模式获得的廉价知识转移到昂贵的常识性知识中。结果是ASER [Zhang等，2020]的转换，这是一种大规模选择的偏好知识资源，转化为transomcs，其表示与ConceptNet相同的表示[Liu and Singh，2004]，但大两个数量级。实验结果证明了语言知识对常识性知识的转移性以及拟议方法在数量，新颖性和质量方面的有效性。 TransOmcs可公开可用：https：//github.com/hkust-knowcomp/transomcs。
Commonsense knowledge acquisition is a key problem for artificial intelligence. Conventional methods of acquiring commonsense knowledge generally require laborious and costly human annotations, which are not feasible on a large scale. In this paper, we explore a practical way of mining commonsense knowledge from linguistic graphs, with the goal of transferring cheap knowledge obtained with linguistic patterns into expensive commonsense knowledge. The result is a conversion of ASER [Zhang et al., 2020], a large-scale selectional preference knowledge resource, into TransOMCS, of the same representation as ConceptNet [Liu and Singh, 2004] but two orders of magnitude larger. Experimental results demonstrate the transferability of linguistic knowledge to commonsense knowledge and the effectiveness of the proposed approach in terms of quantity, novelty, and quality. TransOMCS is publicly available at: https://github.com/HKUST-KnowComp/TransOMCS.
