AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Event Detection via Gated Multilingual Attention Mechanism

AAAI 2018 · Architectures and efficiency › Attention and transformers · approach: Long-context KV and memory attention · 128 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 monolingual context attention (ablation)GMLATT-Mon · ACE 2005EC F1: 68.3 -> 70.4Helped
add multilingual aligned trigger information (ablation)GMLATT-MonATT · ACE 2005EC F1: 70.4 -> 71.2Helped
use gated cross-lingual attention (STG2) instead of aligned trigger (ablation)GMLATT · ACE 2005EC F1: 71.2 -> 72.4Helped
use gated combination STG2 instead of STG1 (ablation)GMLATT · ACE 2005EC F1: 71.7 -> 72.4Helped
add entity embedding (ablation)GMLATT-MonATT · ACE 2005EC F1: 68.4 -> 69.2Helped
add position embedding (ablation)GMLATT-MonATT · ACE 2005EC F1: 68.4 -> 68.8Helped
GMLATT vs best prior methodevent detection · ACE 2005trigger identification F1: 74.3 vs 74.1No clear effect

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