AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Semi-Supervised Learning on Meta Structure: Multi-Task Tagging and Parsing in Low-Resource Scenarios

KyungTae Lim, Jay Yoon Lee, Jaime Carbonell, Thierry Poibeau

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Incomplete multi-view multi-label learning · 25 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
replace concatenated-view baseline with META-BILSTM multi-view structure (ablation)BASELINE parser · UD 2.3 low-resource 9-language avgLAS: 36.2 -> 39.0Improved
add co-training consensus loss on unlabeled data (Co-meta ensemble) (ablation)META-BASE · UD 2.3 low-resource 9-language avgLAS: 39.0 -> 40.3Improved
ensemble-based vs voting-based target extraction (ablation)Co-meta · UD 2.3 low-resource 9-language avgLAS: 39.4 -> 40.3Improved
remove confidence score from consensus loss (ablation)Co-meta · Greek el_bdt 100 train sentsLAS (META): 69.1 -> 67.4Hurt
add Co-meta SSL on Finnish with very few tokens (ablation)META-BASE · Finnish fi_ftbLAS: 21.9 -> 21.8No clear effect
out-of-domain unlabeled data (Wikipedia) instead of in-domain (ablation)Co-meta Ensemble · Chinese zh_gsdLAS: 45.3 -> 46.3Improved
out-of-domain unlabeled data (Wikipedia) instead of in-domain (ablation)Co-meta Ensemble · Greek el_bdtLAS: 69.0 -> 68.7Hurt
add Co-meta SSL in high-resource setting without LM (ablation)META-BASE · English en_ewt full trainLAS: 86.95 -> 87.01No clear effect
add Co-meta SSL with ELMo (ablation)META-BASE · English en_ewt full trainLAS: 88.28 -> 88.25No clear effect
add Co-meta SSL with BERT-Multi (ablation)META-BASE · English en_ewt full trainLAS: 89.49 -> 89.52No clear effect
Co-meta with 5 labeled sentences (ablation)META-BASE/BASELINE · Chinese zh_gsdLASMixed

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