Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy
Despite more than a decade of curriculum learning (CL) research in NLP, the field lacks a principled account of which difficulty function or scheduler to use for a given problem. To understand what has hindered progress towards this account, we propose a fine-grained taxonomy separating difficulty evaluation from training scheduling to enable systematic analysis of CL strategies. For difficulty evaluation, we distinguish attribution source and task dependence, revealing difficulty as a perspectival concept encoding different assumptions about what makes an instance hard to learn. For schedulin
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 84%amitness/learning →
“Fuzzy title match (0.92): “Disentangling Curriculum Learning in NLP: Towards a Unifying” ≈ “amitness/learning””
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Disentangling Curriculum Learning in NLP: Towards a Unifying” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Vanessa Toborek →
“Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy”
- LinkedLinked via arxiv author · 85%Florian Seiffarth →
“Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy”
- LinkedLinked via arxiv author · 85%Sebastian Müller →
“Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy”
- LinkedLinked via arxiv author · 85%Tamás Horváth →
“Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy”