AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Effective Broad-Coverage Deep Parsing

James Allen, Omid Bahkshandeh, William de Beaumont, Lucian Galescu, Choh Man Teng

AAAI 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 11 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
add Enju parser advice on top of CoreNLP advice (ablation)DRUM · 60 biology sentencesEKB F1: 82.21% -> 83.28%Improved
add CoreNLP advice on top of Enju advice (ablation)DRUM · 60 biology sentencesEKB F1: 79.75% -> 83.28%Improved
add statistical parser constituent advice (ablation)DRUM · 60 biology sentencesEKB F1: 69.75% -> 83.28%Improved
add statistical parser constituent advice (ablation)DRUM · 60 biology sentencesSmatch F1: 78.92% -> 87.63%Improved
add WordNet-based lexicon expansion (ablation)DRUM · 60 biology sentencesEKB F1: 82.21% -> 83.28%Improved
add named entity recognition (ablation)DRUM · 60 biology sentencesEKB F1: 12.30% -> 83.28%Improved
add named entity recognition (ablation)DRUM · 60 biology sentencesSmatch F1: 67.82% -> 87.63%Improved
set bracket crossing penalty to 1 (ignore syntactic advice) vs near 1 (0.99) (ablation)DRUM · 60 biology sentencesEKB F1 / Smatch F1Hurt
raise constituent boost factor above low value (0.2) (ablation)DRUM · 60 biology sentencesEKB F1 / Smatch F1Hurt

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