Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction

TL;DR

This paper introduces KLG, a relation extraction method that leverages the Top-k prediction set and label graph to improve accuracy, especially for long-tailed classes, outperforming existing models.

Contribution

The paper proposes a novel Label Graph Network with Top-k Prediction Set (KLG) that utilizes candidate label information and dynamic k-selection for enhanced relation extraction.

Findings

KLG achieves state-of-the-art performance on three datasets.

KLG is more effective for long-tailed relation classes.

Utilizing Top-k prediction sets improves relation prediction accuracy.

Abstract

The typical way for relation extraction is fine-tuning large pre-trained language models on task-specific datasets, then selecting the label with the highest probability of the output distribution as the final prediction. However, the usage of the Top-k prediction set for a given sample is commonly overlooked. In this paper, we first reveal that the Top-k prediction set of a given sample contains useful information for predicting the correct label. To effectively utilizes the Top-k prediction set, we propose Label Graph Network with Top-k Prediction Set, termed as KLG. Specifically, for a given sample, we build a label graph to review candidate labels in the Top-k prediction set and learn the connections between them. We also design a dynamic $k$-selection mechanism to learn more powerful and discriminative relation representation. Our experiments show that KLG achieves the best performances on three relation extraction datasets. Moreover, we observe that KLG is more effective in dealing with long-tailed classes.