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

2018/04/21 by Sheng Zhang, Kevin Duh, Zhang, Sheng +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1804.08000

openalex publication_date 2018/04/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Adam: A Method for Stochastic Optimization
• Long Short-Term Memory
• Context-Dependent Fine-Grained Entity Type Tagging

Related

• An Attentive Neural Architecture for Fine-grained Entity Type Classification
• Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss
• Neural Architectures for Fine-grained Entity Type Classification
• Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representations
• Improving Fine-grained Entity Typing with Entity Linking