Path-Based Attention Neural Model for Fine-Grained Entity Typing
This addresses label noise issues in entity typing for NLP applications, but it is incremental as it builds on existing methods with a new neural approach.
The paper tackles the problem of fine-grained entity typing by proposing an end-to-end model called PAN to handle label noise in distantly supervised training data, achieving effective performance as demonstrated in experiments.
Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure. Traditional distant supervision based methods employ a structured data source as a weak supervision and do not need hand-labeled data, but they neglect the label noise in the automatically labeled training corpus. Although recent studies use many features to prune wrong data ahead of training, they suffer from error propagation and bring much complexity. In this paper, we propose an end-to-end typing model, called the path-based attention neural model (PAN), to learn a noise- robust performance by leveraging the hierarchical structure of types. Experiments demonstrate its effectiveness.