AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning

Daojian Zeng, Haoran Zhang, Qianying Liu

AAAI 2020 · Architectures and efficiency › Attention and transformers · approach: Long-context KV and memory attention · 212 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 linear entity-copying scores with a nonlinear fused-feature layer (ablation)CopyRE · NYTtriplet F1: .571 -> .722Improved
replace linear entity-copying scores with a nonlinear fused-feature layer (ablation)CopyRE · WebNLGtriplet F1: .291 -> .605Improved
replace linear entity-copying scores with a nonlinear fused-feature layer (ablation)CopyRE · NYTentity F1: .647 -> .756Improved
replace linear entity-copying scores with a nonlinear fused-feature layer (ablation)CopyRE · WebNLGentity F1: .595 -> .782Improved
add a sequence-labeling NER task rather than predict entity length in decoder outputs (ablation)CopyRE' · NYTF1: .671 -> .709Improved
add a sequence-labeling NER task rather than predict entity length in decoder outputs (ablation)CopyRE' · WebNLGF1: .553 -> .589Improved
use separate decoders for each triplet instead of shared decoder parameters (ablation)CopyMTL · NYTF1: .709 -> .720Improved
use separate decoders for each triplet instead of shared decoder parameters (ablation)CopyMTL · WebNLGF1: .589 -> .564Hurt
add the entity mask during inference (ablation)CopyMTL · NYT and WebNLGF1No clear effect
remove the entity mask (ablation)CopyRE · NYT and WebNLGF1: zeroHurt
add multi-task sequence labeling to predict complete multi-token entities (ablation)CopyRE' · NYT and WebNLGF1: .671 -> .709; .553 -> .589Improved

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