论文标题
MICO：一个常识性知识表示的多态度对比学习框架
MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation
论文作者
论文摘要
常识性推理任务，例如常识性知识图完成和常识性问题，需要强大的表示。在本文中，我们建议通过MICO学习常识性知识表示，这是一个多态对比度对比度的学习框架（MICO）。 MICO通过实体节点之间的上下文相互作用以及与多态对比度学习之间的上下文相互作用来产生常识性知识表示。在Mico中，以自然语言的形式将$（H，R，T）中的头部和尾部实体转换为两个关系感知的序列对（前提和替代）。 MICO生成的语义表示可以通过简单地比较表示形式之间的距离得分来使以下两个任务受益：1）零射击常识性问题回答任务； 2）感应常识知识图完成任务。广泛的实验显示了我们方法的有效性。
Commonsense reasoning tasks such as commonsense knowledge graph completion and commonsense question answering require powerful representation learning. In this paper, we propose to learn commonsense knowledge representation by MICO, a Multi-alternative contrastve learning framework on COmmonsense knowledge graphs (MICO). MICO generates the commonsense knowledge representation by contextual interaction between entity nodes and relations with multi-alternative contrastive learning. In MICO, the head and tail entities in an $(h,r,t)$ knowledge triple are converted to two relation-aware sequence pairs (a premise and an alternative) in the form of natural language. Semantic representations generated by MICO can benefit the following two tasks by simply comparing the distance score between the representations: 1) zero-shot commonsense question answering task; 2) inductive commonsense knowledge graph completion task. Extensive experiments show the effectiveness of our method.
