XLORE2: Large-scale Cross-lingual Knowledge Graph Construction and Application

Knowledge bases(KBs)are often greatly incomplete,necessitating a demand for KB completion.Although XLORE is an English-Chinese bilingual knowledge graph,there are only 423,974 cross-lingual links between English instances and Chinese instances.We present XLORE2,an extension of the XLORE that is built automatically from Wikipedia,Baidu Baike and Hudong Baike.We add more facts by making cross-lingual knowledge linking,cross-lingual property matching and fine-grained type inference.We also design an entity linking system to demonstrate the effectiveness and broad coverage of XLORE2.

Construction of Multimodal Chinese Tourism Knowledge Graph

With the development of tourism knowledge graphs(KGs),recommendation,question answering(QA)and other functions under its support enable various applications to better understand users and provide services.Existing Chinese tourism KGs do not contain enough entity information and relations.Besides,the knowledge storage usually contains only the text modality but lacks other modalities such as images.In this paper,a multi-modal Chinese tourism knowledge graph(MCTKG)is proposed based on Beijing tourist attractions to support QA and help tourists plan tourism routes.An MCTKG ontology was constructed to maintain the semantic consistency of heterogeneous data sources.To increase the number of entities and relations related to the tourist attractions in MCTKG,entities were automatically expanded belonging to the concepts of building,organization,relic,and person based on Baidu Encyclopedia.In addition,based on the types of tourist attractions and the styles of tourism route,a tourism route generation algorithm was proposed,which can automatically schedule the tourism routes by incorporating tourist attractions and the route style.Experimental results show that the generated tourist routes have similar satisfaction comparedwith the tourism routes crawled from specific travel websites.