atlas

Research map / Graph learning / Graph algorithms and clustering

Global Greedy Dependency Parsing

AAAI 2020 · Graph learning › Graph algorithms and clustering · approach: Continuous DAG structure learning · 35 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
use global greedy parsing instead of the easy-first parserDependency parsing · PTB-SD and CTBLAS: 90.9 -> 94.54; 85.5 -> 89.44Helped
replace greedy decoding with MST decoding (ablation)Global Greedy parser · PTB-SDUAS: 95.83 -> 95.93Helped
replace greedy decoding with MST decoding (ablation)Global Greedy parser · CTBUAS: 90.47 -> 90.55No clear effect
add fixed BERT representationGlobal Greedy parser · PTB-SDUAS: 95.83 -> 96.44Helped
add fixed ELMo and BERT representationsGlobal Greedy parser · PTB-SDUAS: 95.83 -> 96.59Helped
use global greedy parsing rather than B AFDependency parsing · CoNLL 14 treebanksUAS: 90.93 -> 92.05Helped
use global greedy parsing rather than S PDependency parsing · UD 12 treebanksUAS: 93.52 -> 94.55Helped
use global greedy decoding rather than S PDependency parsing · PTB decodingtokens/sec.: 1508 -> 8541Helped

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