Neural Segmental Hypergraphs for Overlapping Mention Recognition

TL;DR

This paper introduces a novel segmental hypergraph model for recognizing overlapping entity mentions, enhancing feature interaction capture and achieving state-of-the-art results with efficient inference.

Contribution

It presents a new hypergraph representation for overlapping mentions, improving over previous models in expressiveness and efficiency, combined with neural networks for feature learning.

Findings

Achieves state-of-the-art performance on benchmark datasets

Models overlapping mentions more effectively than previous methods

Maintains low inference time complexity

Abstract

In this work, we propose a novel segmental hypergraph representation to model overlapping entity mentions that are prevalent in many practical datasets. We show that our model built on top of such a new representation is able to capture features and interactions that cannot be captured by previous models while maintaining a low time complexity for inference. We also present a theoretical analysis to formally assess how our representation is better than alternative representations reported in the literature in terms of representational power. Coupled with neural networks for feature learning, our model achieves the state-of-the-art performance in three benchmark datasets annotated with overlapping mentions.