A Review on Semi-Supervised Relation Extraction
It addresses the problem of high annotation costs in relation extraction for NLP researchers, but is incremental as it reviews existing methods.
This paper reviews three semi-supervised methods for relation extraction to reduce annotation costs, comparing self-ensembling, self-training, and dual learning with specific examples like Mean-teacher, LST, and DualRE.
Relation extraction (RE) plays an important role in extracting knowledge from unstructured text but requires a large amount of labeled corpus. To reduce the expensive annotation efforts, semisupervised learning aims to leverage both labeled and unlabeled data. In this paper, we review and compare three typical methods in semi-supervised RE with deep learning or meta-learning: self-ensembling, which forces consistent under perturbations but may confront insufficient supervision; self-training, which iteratively generates pseudo labels and retrain itself with the enlarged labeled set; dual learning, which leverages a primal task and a dual task to give mutual feedback. Mean-teacher (Tarvainen and Valpola, 2017), LST (Li et al., 2019), and DualRE (Lin et al., 2019) are elaborated as the representatives to alleviate the weakness of these three methods, respectively.