C
Cui Hai
Researcher at Jilin University
Publications - 4
Citations - 21
Cui Hai is an academic researcher from Jilin University. The author has contributed to research in topics: Relation (database) & Relationship extraction. The author has an hindex of 1, co-authored 4 publications receiving 1 citations. Previous affiliations of Cui Hai include Chinese Ministry of Education.
Papers
More filters
Journal ArticleDOI
Simple Question Answering over Knowledge Graph Enhanced by Question Pattern Classification
TL;DR: Zhang et al. as discussed by the authors proposed a pipeline framework for question answering over knowledge graph (KGQA), which consists of three cascaded components: (1) an entity detection model, which can label the entity mention in the question; (2) a question pattern classifier according to the correlations between question patterns and relation types, and (3) a simple yet effective relation detection model which is used to match the semantic similarity between the question and relation candidates.
Journal ArticleDOI
Distantly Supervised Relation Extraction using Global Hierarchy Embeddings and Local Probability Constraints
Alamat Florist,Tao Peng,Tao Peng,Ricardo Rosa Fagundes,Han Ridong,Han Ridong,Cui Hai,Cui Hai,Lin Yue,Jiayu Han,Lu Liu,Lu Liu +11 more
TL;DR: Li et al. as mentioned in this paper constructed an undirected connected graph according to the relation hierarchies, and employed Graph Attention Networks (GATs) to aggregate node information and generate correlation-aware Global Hierarchy Embeddings (GHE).
Posted Content
Distantly Supervised Relation Extraction via Recursive Hierarchy-Interactive Attention and Entity-Order Perception.
TL;DR: RHIA as mentioned in this paper uses the hierarchical structure of the relation to model the interactive information between the relation levels to further handle long-tail relations and introduces a new fangled training objective, called Entity-Order Perception (EOP), to make the sentence encoder retain more entity appearance information.
Patent
Intelligent question-answering method and system
TL;DR: In this paper, an intelligent question answering method and system based on knowledge graph and sub-graph search is presented. But the system is not suitable for answering complex questions, and it cannot answer complex questions with high question answering capability.