Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds
This work addresses entity typing for natural language processing applications, representing an incremental improvement over prior methods.
The paper tackled the problem of fine-grained entity typing by proposing a neural architecture that leverages increased semantic context and adaptive classification thresholds, achieving state-of-the-art results on three benchmark datasets.
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.