AI Paper Atlas

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

Efficient Dependency-Guided Named Entity Recognition

Zhanming Jie, Aldrian Muis, Wei Lu

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 52 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 dependency-guided valid spans instead of unrestricted semi-Markov spansDGM versus Semi-Markov CRFs · OntoNotes 5.0 Broadcast News, given dependencies; dependency featuresF-score: 79.6 -> 80.5Improved
Use dependency-guided valid spans instead of unrestricted semi-Markov spansDGM versus Semi-Markov CRFs · OntoNotes 5.0 Broadcast News, predicted dependencies; dependency featuresF-score: 79.5 -> 79.4No clear effect
Allow valid spans covered by multiple adjacent dependency arcs, rather than only single arcs (ablation)DGM · OntoNotes 5.0 Broadcast News, given dependencies; dependency featuresF-score: 79.0 -> 80.5Improved
Allow valid spans covered by multiple adjacent dependency arcs, rather than only single arcs (ablation)DGM · OntoNotes 5.0 Broadcast News, predicted dependencies; dependency featuresF-score: 78.2 -> 79.4Improved
Allow valid spans covered by multiple adjacent dependency arcs, rather than only single arcs (ablation)DGM · OntoNotes 5.0 Broadcast News, given dependencies; no dependency featuresF-score: 78.6 -> 79.9Improved
Allow valid spans covered by multiple adjacent dependency arcs, rather than only single arcs (ablation)DGM · OntoNotes 5.0 Broadcast News, predicted dependencies; no dependency featuresF-score: 78.0 -> 78.8Improved
Add dependency features (ablation)DGM · OntoNotes 5.0 Broadcast News, given dependenciesF-score: 79.9 -> 80.5Improved
Add dependency features (ablation)DGM · OntoNotes 5.0 Broadcast News, predicted dependenciesF-score: 78.8 -> 79.4Improved
Use predicted rather than given dependency treesDGM · OntoNotes 5.0 Broadcast News; dependency featuresF-score: 80.5 -> 79.4Hurt
Use predicted rather than given dependency treesDGM · OntoNotes 5.0 Broadcast News; no dependency featuresF-score: 79.9 -> 78.8Hurt
Use DGM rather than Semi-Markov CRFsOntoNotes 5.0 Broadcast News · Training time per iterationrelative training time: 47%Improved

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