DeepAI AI Chat
Log In Sign Up

RNNCTPs: A Neural Symbolic Reasoning Method Using Dynamic Knowledge Partitioning Technology

by   Yu-hao Wu, et al.
NetEase, Inc

Although traditional symbolic reasoning methods are highly interpretable, their application in knowledge graph link prediction is limited due to their low computational efficiency. In this paper, we propose a new neural symbolic reasoning method: RNNCTPs, which improves computational efficiency by re-filtering the knowledge selection of Conditional Theorem Provers (CTPs), and is less sensitive to the embedding size parameter. RNNCTPs are divided into relation selectors and predictors. The relation selectors are trained efficiently and interpretably, so that the whole model can dynamically generate knowledge for the inference of the predictor. In all four datasets, the method shows competitive performance against traditional methods on the link prediction task, and can have higher applicability to the selection of datasets relative to CTPs.


page 1

page 2

page 3

page 4


Neural Theorem Provers Delineating Search Area Using RNN

Although traditional symbolic reasoning methods are highly interpretable...

Learning Representations of Bi-Level Knowledge Graphs for Reasoning beyond Link Prediction

Knowledge graphs represent known facts using triplets. While existing kn...

Neural-Symbolic Commonsense Reasoner with Relation Predictors

Commonsense reasoning aims to incorporate sets of commonsense facts, ret...

EM-RBR: a reinforced framework for knowledge graph completion from reasoning perspective

Knowledge graph completion aims to predict the new links in given entiti...

Embedding Cardinality Constraints in Neural Link Predictors

Neural link predictors learn distributed representations of entities and...

IMKGA-SM: Interpretable Multimodal Knowledge Graph Answer Prediction via Sequence Modeling

Multimodal knowledge graph link prediction aims to improve the accuracy ...

Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning

Geometry problem solving has attracted much attention in the NLP communi...