{"id":32416,"date":"2026-01-21T17:01:55","date_gmt":"2026-01-21T17:01:55","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/exploring-curriculum-learning-for-languages-lessons-from-regular-language-tasks\/"},"modified":"2026-06-08T13:20:22","modified_gmt":"2026-06-08T13:20:22","slug":"exploring-curriculum-learning-for-languages-lessons-from-regular-language-tasks","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/exploring-curriculum-learning-for-languages-lessons-from-regular-language-tasks\/","title":{"rendered":"Exploring Curriculum Learning for\u00a0Languages: Lessons from\u00a0Regular Language Tasks"},"content":{"rendered":"<p>Despite its intuitive appeal, the effectiveness of data-level curriculum learning ({CL}) remains debated, mainly due to the absence of unambiguous notions of sample difficulty in real-world tasks. As a step towards a better understanding of the effective use of different curriculum strategies in natural language learning, we study {CL} in the context of regular languages, where both ground truth and sample difficulty can be precisely defined using deterministic finite automata. We consider two natural measures of difficulty: a data-driven metric based on input length and a task-specific metric derived from the automaton\u2019s structure. Training {RNNs} and {LSTMs} across ten regular language classification tasks, we find that {CL} is not just beneficial but, in some cases, essential for generalisation. Surprisingly, straightforward data-driven curricula outperform more complex task-specific strategies, with the most successful approaches oversampling the shorter lengths early in training.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Despite its intuitive appeal, the effectiveness of data-level curriculum learning ({CL}) remains debated, mainly due to the absence of unambiguous notions of sample difficulty in real-world tasks. As a step towards a better understanding of the effective use of different curriculum strategies in natural language learning, we study {CL} in the context of regular languages, where both ground truth and sample difficulty can be precisely defined using deterministic finite automata. [&hellip;]<\/p>\n","protected":false},"author":12,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"class_list":["post-32416","publication","type-publication","status-publish","hentry","publication-type-inproceedings"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32416","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/12"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32416\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=32416"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=32416"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}