Knowledge Graph Completion Method Combined With Adaptive Enhanced Semantic Information

TL;DR

This paper introduces a knowledge graph completion method that adaptively enhances semantic information using BERT-based semantic attention and dimensionality reduction, improving performance on benchmark datasets.

Contribution

It proposes a novel method combining adaptive semantic enhancement with translation models, utilizing BERT fine-tuning and attention mechanisms for improved knowledge graph completion.

Findings

Achieves about 2.6% improvement on FB15K and WIN18 datasets.

Effectively incorporates semantic attention into translation models.

Reduces semantic vector dimensionality with BERT-whitening.

Abstract

Translation models tend to ignore the rich semantic information in triads in the process of knowledge graph complementation. To remedy this shortcoming, this paper constructs a knowledge graph complementation method that incorporates adaptively enhanced semantic information. The hidden semantic information inherent in the triad is obtained by fine-tuning the BERT model, and the attention feature embedding method is used to calculate the semantic attention scores between relations and entities in positive and negative triads and incorporate them into the structural information to form a soft constraint rule for semantic information. The rule is added to the original translation model to realize the adaptive enhancement of semantic information. In addition, the method takes into account the effect of high-dimensional vectors on the effect, and uses the BERT-whitening method to reduce the dimensionality and generate a more efficient semantic vector representation. After experimental comparison, the proposed method performs better on both FB15K and WIN18 datasets, with a numerical improvement of about 2.6% compared with the original translation model, which verifies the reasonableness and effectiveness of the method.