AI Paper Atlas

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

Hierarchical Contextualized Representation for Named Entity Recognition

Ying Luo, Fengshun Xiao, Hai Zhao

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 142 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 sentence-level representation (ablation)IntNet-LSTM-CRF · CoNLL-2003F1: 91.60 -> 91.80Improved
Add document-level representation (ablation)IntNet-LSTM-CRF · CoNLL-2003F1: 91.60 -> 91.79Improved
Add sentence-level and document-level representations (ablation)IntNet-LSTM-CRF · CoNLL-2003F1: 91.60 -> 91.96Improved
Add sentence-level representation (ablation)IntNet-LSTM-CRF · CoNLL-2002F1: 86.65 -> 86.95Improved
Add document-level representation (ablation)IntNet-LSTM-CRF · CoNLL-2002F1: 86.65 -> 86.76Improved
Add sentence-level and document-level representations (ablation)IntNet-LSTM-CRF · CoNLL-2002F1: 86.65 -> 87.08Improved
Add sentence-level representation (ablation)IntNet-LSTM-CRF · OntoNotes 5.0F1: 87.58 -> 87.86Improved
Add document-level representation (ablation)IntNet-LSTM-CRF · OntoNotes 5.0F1: 87.58 -> 87.81Improved
Add sentence-level and document-level representations (ablation)IntNet-LSTM-CRF · OntoNotes 5.0F1: 87.58 -> 87.98Improved
Replace mean pooling with label-embedding attention (ablation)Sentence-level representation on CoNLL-2003 · CoNLL-2003F1: 91.65 -> 91.80Improved
Use scaled dot-product instead of dot-product memory attention (ablation)Document-level representation · CoNLL-2003F1: 91.63 -> 91.75Improved
Use cosine similarity instead of scaled dot-product memory attention (ablation)Document-level representation · CoNLL-2003F1: 91.75 -> 91.79Improved

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