Ultra-Fine Entity Typing

@inproceedings{Choi2018UltraFineET,
  title={Ultra-Fine Entity Typing},
  author={Eunsol Choi and Omer Levy and Yejin Choi and Luke S. Zettlemoyer},
  booktitle={ACL},
  year={2018}
}
We introduce a new entity typing task: given a sentence with an entity mention, the goal is to predict a set of free-form phrases (e.g. skyscraper, songwriter, or criminal) that describe appropriate types for the target entity. This formulation allows us to use a new type of distant supervision at large scale: head words, which indicate the type of the noun phrases they appear in. We show that these ultra-fine types can be crowd-sourced, and introduce new evaluation sets that are much more… CONTINUE READING
5
Twitter Mentions

Citations

Publications citing this paper.
SHOWING 1-10 OF 14 CITATIONS

ERNIE: Enhanced Language Representation with Informative Entities

  • ACL
  • 2019
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

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

  • NAACL-HLT
  • 2019
VIEW 10 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Learning to Denoise Distantly-Labeled Data for Entity Typing

VIEW 24 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Fine-Grained Entity Typing in Hyperbolic Space

Federico López, Benjamin Heinzerling, Michael Strube
  • RepL4NLP@ACL
  • 2019
VIEW 18 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

KCAT: A Knowledge-Constraint Typing Annotation Tool

  • ACL
  • 2019
VIEW 4 EXCERPTS
HIGHLY INFLUENCED

References

Publications referenced by this paper.