An Attentive Neural Architecture for Fine-grained Entity Type Classification

@article{Shimaoka2016AnAN,
  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},
  year={2016},
  volume={abs/1604.05525}
}
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… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 37 CITATIONS

Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing

VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Improving Distantly-supervised Entity Typing with Compact Latent Space Clustering

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

OTyper: A Neural Architecture for Open Named Entity Typing

VIEW 14 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Ultra-Fine Entity Typing

VIEW 6 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Relation Enhanced Neural Model for Type Classification of Entity Mentions with a Fine-Grained Taxonomy

VIEW 6 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Semantic Technology

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Fine-Grained Entity Typing in Hyperbolic Space

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Improving Neural Fine-Grained Entity Typing With Knowledge Attention

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.