Demo

知识库问答系统gAnswer

gAnswer是一个基于开放领域知识图谱的自然语言问答(QA)系统,能够将自然语言问题转化成包含语义信息的查询图,并将查询图转化成标准的SPARQL查询,将这些查询在图数据库(gStore)中执行,最终得到用户的答案。目前英文问答基于DBpedia2016数据集,中文问答基于PKU BASE。

 

  • 相关论文

  1. [1] Sen Hu, Lei Zou, Xinbo Zhang: A State-transition Framework to Answer Complex Questions over Knowledge Base. EMNLP 2018: 2098–2108
  2. [2] Sen Hu, Lei Zou, Haixun Wang, Jeffrey Xu Yu, Wenqiang He: Answering Natural Language Questions by Subgraph Matching over Knowledge Graphs. IEEE TKDE 2017
  3. [3] Shuo Han, Lei Zou, Jeffrey Xu Yu, Dongyan Zhao: Keyword Search on RDF Graphs - A Query Graph Assembly Approach. CIKM 2017: 227-236
  4. [4] Lei Zou, Ruizhe Huang, Haixun Wang, Jeffrey Xu Yu, Wenqiang He, Dongyan Zhao: Natural language question answering over RDF: a graph data driven approach. SIGMOD Conference 2014: 313-324
  5. [5] Weiguo Zheng, Lei Zou, Xiang Lian, Jeffrey Xu Yu, Shaoxu Song, Dongyan Zhao. How to Build Templates for RDF Question/Answering: An Uncertain Graph Similarity Join Approach SIGMOD Conference, 2015.
  6.  
返回