-
5月15日学术报告3(北京大学 : Lei Zou :Natural Language Question Answeri
-
类别:网络整理
发布人:admin
浏览次数: 次
发布时间:2015-09-02 14:24
-
报告题目:Natural Language Question Answering Over Knowledge Graph----A Data-driven Approach
报告日期及时间:5月15日周五上午10点
报告地点: B404报告厅
报告人: Lei Zou 副教授
报告人单位:北京大学
报告人简介:Lei Zou received his BS degree and Ph.D. degree in Computer Science at Huazhong University of Science and Technology (HUST)
in 2003 and 2009, respectively. He received a CCF (China Computer Federation) Doctoral Dissertation Nomination Award in 2009
and won Second Class Prize of CCF Natural Science Award in 2014. Since September 2009, he joined Institute of Computer
Science and Technology (ICST) of Peking University (PKU) as a faculty member. He has been an associate professor in PKU
since August 2012. His recent research interests include graph databases, RDF knowledge graph, particularly in graph-based RDF data management. He has published more than 30 papers, including more than 15 papers published in reputed
journals and major international conferences, such as SIGMOD, VLDB, ICDE, TKDE, VLDB Journal.
报告摘要:
As more and more RDF data become available on the web, the question of how end users can access this body of knowledge
becomes of crucial importance.
Although SPARQL is a standard way to access RDF data, it remains tedious and difficult for end users because of the complexity of the SPARQL syntax and the RDF schema. An ideal system should allow end users to profit from the expressive
power of Semantic Web standards (such as RDF and SPARQLs) while at the same time hiding their complexity behind an intuitive and easy-to use interface. Therefore, RDF question/ answering (Q/A) systems have received wide attention in both NLP (natural language processing) and DB (database) areas.
In this talk, besides reviewing some existing work about RDF Q/A in both NLP and DB areas, we introduce our recent work
along this direction.
Specifically, we design a graph based RDF Q/A system, called gAnswer, representing an natural language question as a
query graph. Then, we answer natural language questions by employing subgraph matching process.
We also present another work, automatically building templates for RDF Q/A, which is based on joining natural language query
workloads and SPARQL query workloads.
邀请人: 彭智勇 教授,彭煜玮 副教授
-
- 上一篇:5月21日学术报告(华中科大 华宇:云存储中近似重复数据删除的系统结构和关键技术 )
- 下一篇:5月15日学术报告2(美国芳邦大学 杨祎:传感器网络中蠕虫攻击的防御)