An Attentive Neural Architecture for Fine-grained Entity Type Classification

Sonse Shimaoka, Pontus Stenetorp, Kentaro Inui, Sebastian Riedel
2016 Proceedings of the 5th Workshop on Automated Knowledge Base Construction  
In this work we propose a novel attentionbased neural network model for the task of fine-grained entity type classification that unlike previously proposed models recursively composes representations of entity mention contexts. Our model achieves state-of-theart performance with 74.94% loose micro F1score on the well-established FIGER dataset, a relative improvement of 2.59% . We also investigate the behavior of the attention mechanism of our model and observe that it can learn contextual
more » ... stic expressions that indicate the fine-grained category memberships of an entity. * This work was conducted during a research visit to University College London.
doi:10.18653/v1/w16-1313 dblp:conf/akbc/ShimaokaSIR16 fatcat:qt6nloof2fdhlfm7txwmwvqgoe