Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction Mingming Sun sunmingming01@baidu.com Big Data Lab (BDL), Baidu Research Xu Li lixu13@baidu.com Big Data Lab (BDL), Baidu Research Xin Wang wangxin60@baidu.com Big Data Lab (BDL), Baidu Research Miao Fan fanmiao@baidu.com Big Data Lab (BDL), Baidu Research Yue Feng fengyue04@baidu.com Big Data Lab (BDL), Baidu Research Ping Li liping11@baidu.com Big Data Lab (BDL), Baidu Research Abstract In this paper, we consider the problem of open information ex- traction (OIE) for extracting entity and relation level intermediate structures from sentences in open-domain. We focus on four types of valuable intermediate structures (Relation, Attribute, Description, and Concept), and propose a unified knowledge expression form, SAOKE, to express them. We publicly release a data set which con- tains 48,248 sentences and the corresponding facts in the SAOKE format labeled by crowdsourcing. T
