RECORD
RNNCTPs: A Neural Symbolic Reasoning Method Using Dynamic Knowledge Partitioning Technology
Artificial Intelligence · Submitted 19 Apr 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim 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.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Although traditional symbolic reasoning methods are highly interpretable, their application in knowledge graph link prediction is limited due to their low computational efficiency. | background 0.96 | 0.05 | 0.03 | asserted 1.00 |
| s1 | 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. | contribution 0.96 | 0.90 | 0.39 | asserted 1.00 |
| s2 | RNNCTPs are divided into relation selectors and predictors. | method 0.99 | 0.56 | 0.03 | asserted 1.00 |
| s3 | The relation selectors are trained efficiently and interpretably, so that the whole model can dynamically generate knowledge for the inference of the predictor. | method 0.99 | 0.79 | 0.08 | asserted 1.00 |
| s4 | 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. | result 0.99 | 0.94 | 0.66 | asserted 0.94 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
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.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 4 sentences without a confident label
Compares with 1 paper
-
Then the focus is on the comparison of RNNNTPs [ref] using attentional selection module, and the comparison of accuracy and performance indicators between CTPs and the set of relations of different embedding dimensions and sizes.
Neural Theorem Provers Delineating Search Area Using RNN · Experimental Setup · 0.98
Cites as background 2 papers
-
Prevailing link prediction methods use neural models such as TransE [ref] , TransR [ref] , RotatE [ref] , RESCAL [ref] , DistMult [ref] , HOLE [ref] , ComplEx [ref] , ConvE [ref] , which have wide applicability.
Embedding Entities and Relations for Learning and Inference in Knowledge Bases · Introduction · 0.94
-
Prevailing link prediction methods use neural models such as TransE [ref] , TransR [ref] , RotatE [ref] , RESCAL [ref] , DistMult [ref] , HOLE [ref] , ComplEx [ref] , ConvE [ref] , which have wide applicability.
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space · Introduction · 0.94
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.