AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

A Recurrent Model for Collective Entity Linking with Adaptive Features

Xiaoling Zhou, Yukai Miao, Wei Wang, Jianbin Qin

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add recurrent global iterations over the initial global model (ablation)RMA · AIDA-Bin-KB accuracy: 89.8 -> 91.5Improved
add local adaptive features to the initial global model (ablation)RMA · AIDA-Bin-KB accuracy: 87.5 -> 89.8Improved
add coherence features (initial global model) to the local model (ablation)RMA · AIDA-Bin-KB accuracy: 85.7 -> 87.5Improved
add novel local features on top of prior-only model (ablation)RMA local model · AIDA-Bin-KB accuracy: 68.2 -> 85.7Improved
gold-entity mention prior bucket from <=0.01 to >0.30RMA · AIDA-Bin-KB accuracy: 57.34% -> 97.94%Improved
gold-entity prior 0.03-0.10 vs 0.01-0.03RMA · AIDA-Bin-KB accuracy: 80.58% -> 75.18%Hurt
compare RMA against Le and Titov 2018 on WIKIRMA · WIKIMicro-F1: 78.0 -> 82.2Improved
compare RMA against Le and Titov 2018 on MSBRMA · MSBMicro-F1: 93.9 -> 93.2Hurt
compare RMA against Ganea and Hofmann 2017 on CWEBRMA · CWEBMicro-F1: 77.9 -> 79.3Improved
compare RMA against Guo and Barbosa 2018 on WIKIRMA · WIKIMicro-F1: 84.5 -> 82.2Hurt
compare RMA against Le and Titov 2018 on AIDA-BRMA · AIDA-Bin-KB accuracy: 93.1 -> 91.5Hurt
compare RMA against Hoffart et al. 2011 on AIDA-BRMA · AIDA-Bin-KB accuracy: 78.0 -> 91.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy