AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

End-to-End Bootstrapping Neural Network for Entity Set Expansion

Lingyong Yan, Xianpei Han, Ben He, Le Sun

AAAI 2020 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning · 7 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
Use BootstrapNet instead of pipelined bootstrapping baselinesBootstrapNet · CoNLLprecision after 20 iterations: less than 70% -> higher than 80%Improved
Use BootstrapNet instead of pipelined bootstrapping baselinesBootstrapNet · OntoNotesprecision after 20 iterations: less than 40% -> higher than 45%Improved
Add the BootstrapEncoder (graph attention) (ablation)BootstrapNet · CoNLL and OntoNotesprecision vs throughputImproved
Add the BootstrapDecoder (GRU sequential expansion) (ablation)BootstrapNet · CoNLL and OntoNotesprecision vs throughputImproved
Remove both encoder and decoder (ablation)BootstrapNet · CoNLL and OntoNotesprecision vs throughputHurt
Increase encoder layers from 1 to 3 (ablation)BootstrapEncoder · CoNLLprecision vs throughputImproved
Increase encoder layers from 1 to 3 (ablation)BootstrapEncoder · OntoNotesprecision vs throughputImproved
Increase encoder layers from 0 to 1 (ablation)BootstrapEncoder · CoNLL and OntoNotesprecision vs throughputImproved
Replace GloVe initialization with random initialization (ablation)BootstrapNet · CoNLLprecision @10 iters: .882 -> .405Hurt
Replace GloVe initialization with random initialization (ablation)BootstrapNet · CoNLLprecision @20 iters: .808 -> .385Hurt
Replace GloVe initialization with random initialization (ablation)BootstrapNet · OntoNotesprecision @10 iters: .521 -> .226Hurt
Replace GloVe initialization with random initialization (ablation)BootstrapNet · OntoNotesprecision @20 iters: .431 -> .206Hurt

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