AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Ensembling Graph Predictions for AMR Parsing

Thanh Lam Hoang, Gabriele Picco, Yufang Hou, Young-Suk Lee, Lam M. Nguyen, Dzung T. Phan, Vanessa López, Ramon Fernandez Astudillo

NeurIPS 2021 · Graph learning › Graph algorithms and clustering · approach: Graph distance and retrieval · 0 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
ensemble four SPRING checkpoints with GrapheneSPRING · AMR 2.0 testSmatch: 84.22 -> 84.78Improved
add APT, T5, Cai&Lam models to the ensemble (Graphene Support vs 4S)Graphene 4S · AMR 2.0 testSmatch: 84.78 -> 85.85Improved
Graphene ensemble of all models vs best single modelSPRING · AMR 3.0 testSmatch: 83.25 -> 84.41Improved
Graphene ensemble on out-of-distribution BIOSPRING · BIOSmatch: 60.52 -> 62.29Improved
select candidate by Smatch instead of support (Graphene Smatch)Graphene Support · AMR 2.0 testSmatch: 85.85 -> 86.26Improved
create pivot-modified graphs versus Barzdins selection onlyBarzdins · New3Smatch: 75.87 -> 76.32Improved
use support as selection criterion instead of SmatchGraphene Smatch · BIOSmatch: 62.80 -> 62.29Mixed
consider every prediction as pivot instead of only SPRING pivot (ablation)Graphene SPRING pivot · AMR 2.0Smatch: 84.70 -> 85.85Improved
use SPRING as sole pivot vs plain SPRING prediction (ablation)SPRING · BIOSmatch: 60.52 -> 61.56Improved
support threshold theta 0.5 instead of 0.1 (ablation)Graphene · AMR 2.0 devSmatch: 81.64 -> 85.49Improved
support threshold theta 0.9 instead of 0.5 (ablation)Graphene · AMR 2.0 devSmatch: 85.49 -> 83.68Hurt
compare Graphene to uniform sampling baseline (ablation)uniform Sampling · BIOSmatch: 56.00 -> 62.29Improved

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