AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Graph Convolutional Networks With Argument-Aware Pooling for Event Detection

AAAI 2018 · Graph learning › Graph self-supervised learning · approach: Graph domain adaptation · 397 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 GCN layers over dependency trees on top of BiLSTM (ablation)BiLSTM event detector · ACE 2005 devF1: 70.5 -> 71.8Helped
add BiLSTM before GCNs (ablation)GCN-ED · ACE 2005 devF1: 71.2 -> 71.8Helped
increase GCN layers from 2 to 3 (ablation)BiLSTM + GCNs · ACE 2005 devF1: 71.8 -> 67.1Hurt
entity mention-based pooling instead of anchor pooling (ablation)GCN-ED · ACE 2005 testF1: 71.4 -> 73.1Helped
entity mention-based pooling instead of overall/dynamic pooling (ablation)GCN-ED · ACE 2005 testF1: 70.8 -> 73.1Helped
entity mention-based pooling with predicted entity mentions (ablation)GCN-ED · TAC KBP 2015 testF1: 57.9 -> 58.8Helped
GCN-ED vs single-model SOTA ATT+event detection · ACE 2005 testF1: 71.9 -> 73.1Helped

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