An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge

2017 ACL WQ42.9
Candidate Generation
Freebase API method is able to resolve as many as 86% questions if we use the top1 result
After getting the topic entity, we collect all the entities directly connected to it and the ones connected with 2-hop5

Overview
An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global
1)从问题当中,确认topic entity,从Freebase党章产生候选答案
2)一个交叉神经网络去表示,问题和答案
3)相似度函数,计算相似度

we employ four kinds of answer aspects:
answer entity ae
answer relation ar,
answer type at
answer context ac
An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global

相关文章:

  • 2021-07-22
  • 2021-07-28
  • 2021-04-13
  • 2021-06-10
  • 2021-12-07
  • 2021-06-09
  • 2021-05-27
  • 2021-08-20
猜你喜欢
  • 2021-07-03
  • 2021-10-07
  • 2022-12-23
  • 2021-07-11
  • 2022-01-10
  • 2021-12-23
  • 2021-06-11
相关资源
相似解决方案