DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction
arXiv:1811.02166
Abstract
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.
arXiv commentAccepted by ACL 2019
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Snorkel: Rapid Training Data Creation with Weak Supervision
- Understanding Neural Networks through Representation Erasure
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
- Reinforcement Learning for Relation Classification from Noisy Data
- Learning the Structure of Generative Models without Labeled Data
- Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix
- Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data