AI Paper Atlas

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

Relation Extraction Exploiting Full Dependency Forests

Lifeng Jin, Linfeng Song, Yue Zhang, Kun Xu, Wei-Yun Ma, Dong Yu

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 32 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
replace 1-best tree (GRN) with full dependency forest (DDCNN)relation extraction model · BioCreative VI CPR testF1: 51.4 -> 53.1Improved
add parser fine-tuning on RE loss to pretrained forest model (ablation)FOREST-DDCNN · BioCreative VI CPR testF1: 53.1 -> 55.7Improved
use data-dependent CNN instead of regular CNN for forests (ablation)FOREST-DDCNN · BioCreative VI CPR testF1: 50.5 -> 53.1Improved
encode 1-best trees with DDCNN instead of GRN (ablation)TREE-GRN · BioCreative VI CPR testF1: 51.4 -> 50.3Hurt
pretrain parser on treebank rather than random init with fine-tuning (ablation)FORESTFT-DDCNN · BioCreative VI CPR testF1: 45.4 -> 55.7Improved
use parser-derived forest probabilities instead of uniform weights (syntax) (ablation)DDCNN · BioCreative VI CPR testF1: 50.4 -> 53.1Improved
fine-tune randomly initialized parser on RE loss vs fixed uniform forest (ablation)DDCNN · BioCreative VI CPR testF1: 50.4 -> 45.4Hurt
FORESTFT-DDCNN vs TREE-GRN with only 1K parser training treesrelation extraction model · BioCreative VI CPR testF1: 47.6 -> 51.5Improved
FORESTFT-DDCNN vs TREE-GRN with 5K parser training treesrelation extraction model · BioCreative VI CPR testF1: 50.3 -> 53.7Improved
forest + parser fine-tuning vs 1-best treeTREE-GRN · PGR testF1: 78.9 -> 89.3Improved
forest + parser fine-tuning vs 1-best treeTREE-GRN · SemEval-2010 Task 8 testF1: 84.6 -> 85.5Improved

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