AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Chinese NER with Height-Limited Constituent Parsing

Rui Wang, Xin Xin, Wei Chang, Kun Ming, Biao Li, Xin Fan

AAAI 2019 · Learning theory and algorithms › Combinatorial and search optimization · approach: Heuristic and local search algorithms

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 height-limited constituent parsing to joint POS+CWS semi-CRF (ablation)semi-CRF with attention + POS + CWS · OntoNotes 4.0 testF1: 75.67 -> 76.67Improved
add height-limited constituent parsing (ablation)semi-CRF with POS+CWS · OntoNotes 4.0 devF1: 74.98 -> 75.37Improved
add height-limited parsing for OOV entities (ablation)semi-CRF with POS+CWS · OntoNotes 4.0 testOOV recall: 64.70 -> 66.38Improved
add POS tagging and word segmentation to AtSemiCRF (ablation)AtSemiCRF · OntoNotes 4.0 testF1: 75.42 -> 75.67Improved
replace LSTM span feature with attention-based span feature in semi-CRF (ablation)SRSemiCRF · OntoNotes 4.0 testF1: 73.78 -> 75.42Improved
use subtraction LSTM span features instead of SR span features (ablation)SRSemiCRF · OntoNotes 4.0 testF1: 73.78 -> 74.77Improved
semi-CRF vs BIO-CRF with lattice LSTM (ablation)Zhang18Latt · OntoNotes 4.0 testF1: 73.88 -> 75.42Improved
joint model on OOV entities vs previous methods (ablation)Zhang18Latt · OntoNotes 4.0 testOOV recall: 60.04 -> 66.38Improved
add parsing to semi-CRF for word segmentation (ablation)SemiCRF · OntoNotes 4.0 word segmentationF1: 95.30 -> 95.45Improved
add parsing to semi-CRF for POS tagging (ablation)SemiCRF · OntoNotes 4.0 POS taggingF1: 83.99 -> 84.40Improved
unified model vs SemiCRF on long entities (length above 7) (ablation)SemiCRF · OntoNotes 4.0 testF1: 70.26 -> 74.42Improved
unified model vs semi-CRF+POS+CWS in decoding time (ablation)SemiCRF+POS+CWS · test set 4636 sentencesavg time per sentence: 0.70s -> 1.00sHurt

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