GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition
This addresses the problem of reducing manual effort in rule creation for NER, but it is incremental as it builds on existing weakly supervised methods.
The paper tackles the challenge of manually devising labeling rules for weakly supervised named entity recognition by proposing GLaRA, a graph-based framework that learns new rules from unlabeled data, resulting in an average improvement of +20% F1 score over baselines on three datasets.
Instead of using expensive manual annotations, researchers have proposed to train named entity recognition (NER) systems using heuristic labeling rules. However, devising labeling rules is challenging because it often requires a considerable amount of manual effort and domain expertise. To alleviate this problem, we propose \textsc{GLaRA}, a graph-based labeling rule augmentation framework, to learn new labeling rules from unlabeled data. We first create a graph with nodes representing candidate rules extracted from unlabeled data. Then, we design a new graph neural network to augment labeling rules by exploring the semantic relations between rules. We finally apply the augmented rules on unlabeled data to generate weak labels and train a NER model using the weakly labeled data. We evaluate our method on three NER datasets and find that we can achieve an average improvement of +20\% F1 score over the best baseline when given a small set of seed rules.