Papers › Ultra-Fine Entity Typing

Ultra-Fine Entity Typing

13 Jul 2018ACL 2018 7arXiv:1807.04905archive 2025-07-28

Eunsol Choi, Omer Levy, Yejin Choi, Luke Zettlemoyer

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 diverse and fine-grained than existing benchmarks. We present a model that can predict open types, and is trained using a multitask objective that pools our new head-word supervision with prior supervision from entity linking. Experimental results demonstrate that our model is effective in predicting entity types at varying granularity; it achieves state of the art performance on an existing fine-grained entity typing benchmark, and sets baselines for our newly-introduced datasets. Our data and model can be downloaded from: http://nlp.cs.washington.edu/entity_type

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

uwnlp/open_type officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Entity LinkingEntity TypingSentence

Datasets

Introduced by this paper, per the archive.

Open Entity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Entity Typing Ontonotes v5 (English) Choi et al. (2018) w augmentation F1 32.0 #4 of 4 Archive leaderboard report
Entity Typing Ontonotes v5 (English) Choi et al. (2018) w augmentation Precision 47.1 #4 of 4 Archive leaderboard report
Entity Typing Ontonotes v5 (English) Choi et al. (2018) w augmentation Recall 24.2 #4 of 4 Archive leaderboard report
Entity Typing Open Entity UFET-biLSTM F1 31.3 #13 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections