AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction

Tapas Nayak, Hwee Tou Ng

AAAI 2020 · Large language models › Language, safety and interpretability · approach: Controlled text generation · 252 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 WDec instead of HRLJoint entity and relation extraction · NYT29F1: 3.9%Improved
Use PNDec instead of HRLJoint entity and relation extraction · NYT24F1: 1.3%Improved
Use a five-run ensemble instead of a single modelWDec and PNDec · NYT29 and NYT24F1: 4.2% and 3.5% higher F1 scores; 4.2% and 2.9% higher F1 scoresImproved
Add masking-based copy to WDec (ablation)WDec · NYT29 and NYT24F1: 0.575 -> 0.626; 0.724 -> 0.775; 0.560 -> 0.610; 0.738 -> 0.776; 0.607 -> 0.682; 0.763 -> 0.817Improved
Use single attention rather than average or N-gram attention (ablation)WDec · NYT29 and NYT24F1: 0.575, 0.560, 0.607; 0.724, 0.738, 0.763Improved
Use combo attention instead of decoder-hidden-only attention (ablation)PNDec · NYT29 and NYT24F1: 0.663 -> 0.673; 0.785 -> 0.789Improved
Use combo attention instead of previous-tuple-only attention (ablation)PNDec · NYT29 and NYT24F1: 0.665 -> 0.673; 0.784 -> 0.789Improved
Decode an entire tuple per step with pointers rather than one word at a timePNDec compared with WDec · NYT29 and NYT24training and inference speed: more than two times fasterImproved
Decode an entire tuple per step with pointers rather than one word at a timePNDec compared with WDec · NYT29 and NYT24GPU memory consumption: one-thirdImproved

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