Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction
This work addresses relation extraction for NLP applications, offering an incremental improvement by utilizing overlooked Top-k information.
The paper tackles relation extraction by proposing a method that leverages the Top-k prediction set to improve label prediction, achieving state-of-the-art performance on three datasets and showing effectiveness for long-tailed classes.
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.