NeuInfer: Knowledge Inference on N-ary Facts

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6141–6151 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 6141 NeuInfer: Knowledge Inference on N-ary Facts Saiping Guan, Xiaolong Jin, Jiafeng Guo, Yuanzhuo Wang, and Xueqi Cheng School of Computer Science and Technology, University of Chinese Academy of Sciences; CAS Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences {guansaiping,jinxiaolong,guojiafeng,wangyuanzhuo,cxq}@ict.ac.cn Abstract Knowledge inference on knowledge graph has attracted extensive attention, which aims to find out connotative valid facts in knowledge graph and is very helpful for improving the per- formance of many downstream applications. However, researchers have mainly poured at- tention to knowledge inference on binary facts. The studies on n-ary facts are relatively scarcer, although they are also ubiquitous in the real world. Therefore, this paper addresses knowl- edge inference on n-ary facts. We represent each n-ary fact as a primary triple coupled with a set of its auxiliary descriptive attribute-value pair(s). We further propose a neural network model, NeuInfer, for knowledge inference on n-ary facts. Besides handling the common task to infer an unknown element in a whole fact, NeuInfer can cope with a new type of task, flexible knowledge inference. It aims to infer an unknown element in a partial fact consisting of the primary triple coupled with any number of its auxiliary description(s). Experimental results demonstrate the remarkable superiority of NeuInfer. 1 Introduction With the introduction of connotative valid facts, knowledge inference on knowledge graph improves the performance of many downstream applica- tions, such as vertical search and question answer- ing (Dong et al., 2015; Lukovnikov et al., 2017). Existing studies (Nickel et al., 2016; Wang et al., 2017) mainly focus on knowledge inference on binary facts with two entities connected with a cer- tain binary relation, represented as triples, (head entity, relation, tail entity). They attempt to infer the unknown head/tail entity or the unknown rela- tion of a given binary fact. However, n-ary facts involving more than two entities are also ubiquitous. For example, in Freebase, more than 1/3 entities participate in n-ary facts (Wen et al., 2016). The fact that John Bardeen received Nobel Prize in Physics in 1956 together with Walter Houser Brattain and William Shockley1 is a typical 5- ary fact. So far, only a few studies (Wen et al., 2016; Zhang et al., 2018; Guan et al., 2019) have tried to address knowledge inference on n-ary facts. In existing studies for knowledge inference on n- ary facts, each n-ary fact is represented as a group of peer attributes and attribute values. In prac- tice, for each n-ary fact, there is usually a primary triple (the main focus of the n-ary fact), and other attributes along with the corresponding attribute values are its auxiliary descriptions. Take the above 5-ary fact for example, the primary triple is (John Bardeen, award-received, Nobel Prize in Physics), and other attribute-value pairs in- cluding point-in-time : 1956, together-with : Walter Houser Brattain and together-with …

Content truncated to 500 words