English

An Attentive Neural Architecture for Fine-grained Entity Type Classification

Computation and Language 2016-04-20 v1

Abstract

In this work we propose a novel attention-based 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-the-art performance with 74.94% loose micro F1-score 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 linguistic expressions that indicate the fine-grained category memberships of an entity.

Keywords

Cite

@article{arxiv.1604.05525,
  title  = {An Attentive Neural Architecture for Fine-grained Entity Type Classification},
  author = {Sonse Shimaoka and Pontus Stenetorp and Kentaro Inui and Sebastian Riedel},
  journal= {arXiv preprint arXiv:1604.05525},
  year   = {2016}
}

Comments

6 pages, 2 figures

R2 v1 2026-06-22T13:35:43.661Z