Abstract
The sentence-level relation extraction mainly aims to classify the relation between two entities in a sentence. The sentence-level relation extraction corpus is often containing data of difficulty for the model to infer or noise data. In this paper, we propose a curriculum learning-based relation extraction model that split data by difficulty and utilize it for learning. In the experiments with the representative sentence-level relation extraction datasets, TACRED and Re-TACRED, the proposed method showed good performances.
Abstract (translated)
URL
https://arxiv.org/abs/2107.09332