A Relational Triple Extraction Method Based on Feature Reasoning for Technological Patents

TL;DR

This paper introduces a feature reasoning-based relational triple extraction method tailored for technological patents, improving efficiency and accuracy by integrating entity recognition and relationship inference.

Contribution

It proposes a novel table filling approach that enhances speed and captures implicit relationships, addressing overlap and bias issues in patent relation extraction.

Findings

Outperforms previous methods on benchmark datasets

Enhances extraction accuracy through feature reasoning

Increases model efficiency and speed

Abstract

The relation triples extraction method based on table filling can address the issues of relation overlap and bias propagation. However, most of them only establish separate table features for each relationship, which ignores the implicit relationship between different entity pairs and different relationship features. Therefore, a feature reasoning relational triple extraction method based on table filling for technological patents is proposed to explore the integration of entity recognition and entity relationship, and to extract entity relationship triples from multi-source scientific and technological patents data. Compared with the previous methods, the method we proposed for relational triple extraction has the following advantages: 1) The table filling method that saves more running space enhances the speed and efficiency of the model. 2) Based on the features of existing token pairs and table relations, reasoning the implicit relationship features, and improve the accuracy of triple extraction. On five benchmark datasets, we evaluated the model we suggested. The result suggest that our model is advanced and effective, and it performed well on most of these datasets.