Question Answering over Knowledge Bases




上午 9:00-11:00






Question Answering over Knowledge Bases


Wanyun Cui

Fudan University

Wanyun Cui is a PhD candidate in the school of computer science at Fudan University, advised by Prof. Wei Wang and Prof. Yanghua Xiao. His research interests include data mining, question answering, and knowledge base. He has been working on building QA systems in Microsoft Research Asia, Baidu deep search group, and Xiaoi Robot since 2012. He has published five papers as the first author in VLDB 2017, IJCAI 2016, AAAI 2016, SIGMOD 2014, and SIGMOD 2013. He received his BS degree from Fudan University in 2013.


Question answering (QA) has become a popular way for humans to access billion-scale knowledge bases. Unlike web search, QA over a knowledge base gives out accurate and concise results, provided that natural language questions can be understood and mapped precisely to structured queries over the knowledge base. In this talk, I will introduce the KBQA project, which involves the study of entities, short texts, questions, and domain adaptation. In particular, I will elaborate QA with a multi-granularity deep neural network.