An Attentive Neural Architecture for Fine-grained Entity Type Classification

In this work we propose a novel attentionbased network model for the task of -grained entity type classification that unlike proposed models recursively representations of entity mention . Our model achieves state-of-theart with 74.94% loose micro F1- on the well-established FIGER dataset, relative improvement of 2.59% . We also investigate behavior of the attention mechanism our model and observe that it can learn linguistic expressions that indicate fine-grained category memberships of an .