AI Paper Atlas

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

Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages

Katharina Kann, Ophélie Lacroix, Anders Søgaard

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 16 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
Use cross-lingual ambiguous-label annotation instead of unsupervised clusteringPOS tagging on 15 truly low-resource languages · 15 truly low-resource languages (average)accuracy: 0.3440 -> 0.4138Improved
Use cross-lingual most-frequent-tag annotation instead of ambiguous-label annotationCross-lingual POS tagging · 15 truly low-resource languages (average)accuracy: 0.4138 -> 0.4106; difference between AMB and FREQ is 0.0032No clear effect
Add character-level word autoencoding auxiliary task to AMB (ablation)AMB · 15 truly low-resource languages (average)accuracy: 0.4138 -> 0.4225Improved
Add character-level word autoencoding auxiliary task to FREQ (ablation)FREQ · 15 truly low-resource languages (average)accuracy: 0.4106 -> 0.4117Hurt
Add a next-word log-frequency language-modeling auxiliary task (ablation)PLA16 · 15 truly low-resource languages (average)accuracy: 0.4138 -> 0.3899Hurt
Use higher-quality dictionaries and UD training texts instead of comparable resourcesAMB · 5 high-resource languages (average)accuracy: 0.43 -> 0.72Improved
Use higher-quality dictionaries and UD training texts instead of comparable resourcesFREQ · 5 high-resource languages (average)accuracy: 0.50 -> 0.77Improved

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