Title: Language understanding with knowledge graphsAbstract： One of the bottlenecks in machine intelligence is that machines have limited cognitive capability to understand data or text in the form of human language. Recently, with more and more online knowledge bases (also known as knowledge graphs) being published, we have a brand new opportunity to empower machines with the capability to understand natural language. In this tutorial, I will systematically review the recent progress in enabling machines with the cognitive ability to understand natural language and discuss some open problems. Specifically, we will introduce (1) the preliminary concepts of knowledge graphs, (2) the recent process about knowledge graph construction, (3) language understanding models and algorithms based on knowledge graphs, (4) applications empowered with knowledge graphs, such as QA on knowledge base, knowledgeable search and recommendation.
Yanghua Xiao got his PHD degree in software theory from Fudan University, Shanghai, China, in 2009. He now is an associate professor of computer science at Fudan University. His research interest includes big data management and mining, graph database, knowledge graph. He won the Best Phd Thesis Nomination of CCF (Chinese Computer Federation)，CCF Natural Science Award (second level), ACM(CCF) Shanghai distinguished young scientists nomination award. Recently, he has published 70+ papers in top-tier international journals and conferences, including TKDE, SIGMOD, VLDB, ICDE, IJCAI, AAAI. He is the PI or Co-PI of 30+ projects supported by 10+ National and Local funding agency and big companies including Microsoft, IBM, HUAWEI, China Telecom, China Mobile, Baidu, XiaoI Robot etc. He regularly serves as the reviewer of 10+ national and local funding agencies and PC members of 50+ top conferences including IJCAI, AAAI, SIGKDD, ICDE, WWW, CIKM, ICDM, SDM etc. He is the Associate Editor of Frontier of Computer Science, and reviewers of 10+ leading journals such as Plos One, IEEE Tansaction on Computers, TKDE. He is a member of ACM, IEEE, AAAI and senior member of CCF. He is the director of Knowledge Works at FUDAN Uni. He built the first knowledge service platform in China (kw.fudan.edu.cn), which serves industries with 200Millions+ API calls. He is the chief scientist or senior advisors of many top Chinese big data companies or AI companies.
Deqing Yang is an associate professor in School of Data Science at Fudan University, who got his Ph.D of Computer Science in 2013 from School of Computer Science at Fudan University. Prof. Yang’s main research interests include database and machine learning, especially for knowledge graph with applications to recommender systems and social network mining. Yang's research publications have been recognized by many notable international conferences in data mining and related fields, including ICDM, WWW, ECML, CIKM, DASFAA and etc.
Wanyun Cui is a PhD candidate in the school of computer science at Fudan University, advised by Prof Yanghua Xiao and Wei Wang. His research interests include question answering and knowledge graph. He has been working on QA systems at Microsoft Research Asia, Baidu (Chinese largest search engine), and Xiaoi Robot since 2012. He has published papers as the first author in top conferences such as VLDB 2017, IJCAI 2016, AAAI 2016, SIGMOD 2014, and SIGMOD 2013. He received his bachelor's degree from Fudan University in 2013.