Multiple Relations Classification using Imbalanced Predictions Adaptation

TL;DR

This paper introduces a novel multiple relations classification model that effectively handles imbalanced predictions and improves performance in relation classification tasks, especially in biomedical and knowledge graph applications.

Contribution

It presents the first approach to explicitly address imbalanced predictions in relation classification using a customized output architecture and additional input features.

Findings

Significant performance improvements on benchmark datasets

Effective handling of imbalanced relation predictions

First to recognize imbalanced predictions in relation classification

Abstract

The relation classification task assigns the proper semantic relation to a pair of subject and object entities; the task plays a crucial role in various text mining applications, such as knowledge graph construction and entities interaction discovery in biomedical text. Current relation classification models employ additional procedures to identify multiple relations in a single sentence. Furthermore, they overlook the imbalanced predictions pattern. The pattern arises from the presence of a few valid relations that need positive labeling in a relatively large predefined relations set. We propose a multiple relations classification model that tackles these issues through a customized output architecture and by exploiting additional input features. Our findings suggest that handling the imbalanced predictions leads to significant improvements, even on a modest training design. The results demonstrate superiority performance on benchmark datasets commonly used in relation classification. To the best of our knowledge, this work is the first that recognizes the imbalanced predictions within the relation classification task.