Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds

TL;DR

This paper introduces a neural model for fine-grained entity typing that leverages extensive context and adaptive thresholds, achieving state-of-the-art results without hand-crafted features.

Contribution

It presents a novel neural architecture that utilizes broader discourse context and adaptive classification thresholds for improved entity typing accuracy.

Findings

Additional context enhances typing performance.

Adaptive thresholds further improve results.

Achieves state-of-the-art on three benchmarks.

Abstract

Fine-grained entity typing is the task of assigning fine-grained semantic types to entity mentions. We propose a neural architecture which learns a distributional semantic representation that leverages a greater amount of semantic context -- both document and sentence level information -- than prior work. We find that additional context improves performance, with further improvements gained by utilizing adaptive classification thresholds. Experiments show that our approach without reliance on hand-crafted features achieves the state-of-the-art results on three benchmark datasets.