scholarly journals A Knowledge Graph Based Solution for Entity Discovery and Linking in Open-Domain Questions

2018 ◽  
pp. 181-190
Author(s):  
Kai Lei ◽  
Bing Zhang ◽  
Yong Liu ◽  
Yang Deng ◽  
Dongyu Zhang ◽  
...  
Keyword(s):  
Knowledge Graph ◽  
Open Domain ◽  
Entity Discovery

Open Domain Question Answering using Knowledge Graph

2020 ◽  
Vol 47 (9) ◽  
pp. 853-862
Author(s):  
Giho Lee ◽  
Incheol Kim
Keyword(s):  
Question Answering ◽  
Knowledge Graph ◽  
Open Domain

scholarly journals Knowledge Graph Grounded Goal Planning for Open-Domain Conversation Generation

2020 ◽  
Vol 34 (05) ◽  
pp. 9338-9345
Author(s):  
Jun Xu ◽  
Haifeng Wang ◽  
Zhengyu Niu ◽  
Hua Wu ◽  
Wanxiang Che
Keyword(s):  
Lower Layer ◽  
Middle Layer ◽  
Knowledge Graph ◽  
Open Domain ◽  
User Interest ◽  
Practical Applications ◽  
Sequence Planning ◽  
User Interests ◽  
Hierarchical Reinforcement Learning ◽  
High Level

Previous neural models on open-domain conversation generation have no effective mechanisms to manage chatting topics, and tend to produce less coherent dialogs. Inspired by the strategies in human-human dialogs, we divide the task of multi-turn open-domain conversation generation into two sub-tasks: explicit goal (chatting about a topic) sequence planning and goal completion by topic elaboration. To this end, we propose a three-layer Knowledge aware Hierarchical Reinforcement Learning based Model (KnowHRL). Specifically, for the first sub-task, the upper-layer policy learns to traverse a knowledge graph (KG) in order to plan a high-level goal sequence towards a good balance between dialog coherence and topic consistency with user interests. For the second sub-task, the middle-layer policy and the lower-layer one work together to produce an in-depth multi-turn conversation about a single topic with a goal-driven generation mechanism. The capability of goal-sequence planning enables chatbots to conduct proactive open-domain conversations towards recommended topics, which has many practical applications. Experiments demonstrate that our model outperforms state of the art baselines in terms of user-interest consistency, dialog coherence, and knowledge accuracy.

Research on Construction of Knowledge Graph of Intestinal Cells

2020 ◽  
Author(s):  
Fengfeng He ◽  
Ling Zhang ◽  
Wei Qu ◽  
Chong Teng ◽  
Dan Xie
Keyword(s):  
Knowledge Graph ◽  
Intestinal Cells ◽  
Construction Of Knowledge
Sign in / Sign up

Export Citation Format

Share Document