Demo

Demo

gAnswer：Question Answering System Based on Knowledge Base

gAnswer is a natural language question answering (QA) system based on open domain knowledge graphs, which can convert natural language questions into query graphs containing semantic information, and convert query graphs into standard SPARQL queries, and place these queries in the graph database (gStore ), And finally get the user's answer. At present, English Q & A is based on the DBpedia2016 dataset, and Chinese Q & A is based on PKU BASE.

 

  • Related Papers

  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.  
  1.  
返回