DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction
It addresses the labor-intensive pattern writing needed for relation extraction, enabling quicker generalization to new relation types, which is an incremental improvement for NLP researchers and practitioners.
The paper tackles the problem of labeling noise in distantly supervised neural relation extraction by proposing DIAG-NRE, a framework that automatically summarizes and refines relational patterns with human input, resulting in significant and interpretable improvements over state-of-the-art methods on two real-world datasets.
Pattern-based labeling methods have achieved promising results in alleviating the inevitable labeling noises of distantly supervised neural relation extraction. However, these methods require significant expert labor to write relation-specific patterns, which makes them too sophisticated to generalize quickly.To ease the labor-intensive workload of pattern writing and enable the quick generalization to new relation types, we propose a neural pattern diagnosis framework, DIAG-NRE, that can automatically summarize and refine high-quality relational patterns from noise data with human experts in the loop. To demonstrate the effectiveness of DIAG-NRE, we apply it to two real-world datasets and present both significant and interpretable improvements over state-of-the-art methods.