A question answering model over food domain knowledge base from two-dimensional Chinese semantic analysis
[1]Zuo Min,Xu Zelong,Zhang Qingchuan,et al.A question answering model over food domain knowledge base from two-dimensional Chinese semantic analysis[J].Journal of Zhengzhou University (Engineering Science),2020,41(03):8-13.[doi:10.13705/j.issn.1671-6833.2020.02.003]
Copy
Journal of Zhengzhou University (Engineering Science)[ISSN
1671-6833/CN
41-1339/T] Volume:
41卷
Number of periods:
2020 03
Page number:
8-13
Column:
Public date:
2020-07-29
- Title:
- A question answering model over food domain knowledge base from two-dimensional Chinese semantic analysis
- Keywords:
- National Engineering Laboratory for Food Safety Traceability Technology and Application of Agricultural Products; Beijing Technology and Business University
- CLC:
- -
- DOI:
- 10.13705/j.issn.1671-6833.2020.02.003
- Abstract:
- Simple Question Answering over Knowledge Bases (KB-QA) is a hot topic in Natural Language Processing (NLP) research, and it is also the most widely used case in real life. However, in the process of researching Chinese KB-QA, there are still many technical challenges such as extracting relations from questions which relation names are ambiguous, also have problems such as error propagation between different processes. Based on the self-built food domain knowledge base (FD-KB) and the food field corpus, this paper starts from the two semantic perspectives of Chinese characters and Chinese words to extract relations and mitigate the error propagation. Contrast experimental results show, the model of two-dimensional Chinese semantic analysis that proposed here can get the accuracy of 85.66%.
- References:
- -
- Similar References:
Memo
-
Last Update:
2020-07-28