FGNET-RH: Fine-Grained Named Entity Typing via Refinement in Hyperbolic Space

TL;DR

This paper introduces FGNET-RH, a hyperbolic space-based framework that leverages hierarchical structures and graph refinement to improve fine-grained named entity typing accuracy, especially under noisy distant supervision.

Contribution

The paper presents a novel hyperbolic geometry approach combined with graph structures for better entity typing, addressing label noise and hierarchical data modeling in FG-NET.

Findings

Improves FG-NET accuracy by up to 3.5%

Effectively models hierarchical entity types

Enhances noise robustness in entity classification

Abstract

Fine-Grained Named Entity Typing (FG-NET) aims at classifying the entity mentions into a wide range of entity types (usually hundreds) depending upon the context. While distant supervision is the most common way to acquire supervised training data, it brings in label noise, as it assigns type labels to the entity mentions irrespective of mentions context. In attempts to deal with the label noise, leading research on the FG-NET assumes that the fine-grained entity typing data possesses a euclidean nature, which restraints the ability of the existing models in combating the label noise. Given the fact that the fine-grained type hierarchy exhibits a hierarchical structure, it makes hyperbolic space a natural choice to model the FG-NET data. In this research, we propose FGNET-RH, a novel framework that benefits from the hyperbolic geometry in combination with the graph structures to perform entity typing in a performance-enhanced fashion. FGNET-RH initially uses LSTM networks to encode the mention in relation with its context, later it forms a graph to distill/refine the mention encodings in the hyperbolic space. Finally, the refined mention encoding is used for entity typing. Experimentation using different benchmark datasets shows that FGNET-RH improves the performance on FG-NET by up to 3.5-% in terms of strict accuracy.