{"id":"W4409348085","doi":"10.1609/aaai.v39i23.34697","title":"Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Northern Alberta Institute of Technology; Mila - Quebec Artificial Intelligence Institute; Queen's University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Alberta Innovates; DeepMind","keywords":"Dependency (UML); Dependency grammar; Computer science; Diversity (politics); Ensemble learning; Parsing; Artificial intelligence; Natural language processing; Statistics; Mathematics; Sociology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001094825,0.0002126713,0.0002613423,0.0001828751,0.0006767713,0.0003158812,0.002459818,0.0001080749,0.00002213117],"category_scores_gemma":[0.0004594676,0.0001729246,0.000111476,0.0005799083,0.000111953,0.000597007,0.000700523,0.0002715068,0.00001770721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006233383,"about_ca_system_score_gemma":0.0001188342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002501667,"about_ca_topic_score_gemma":0.00008714997,"domain_scores_codex":[0.9981126,0.00006095303,0.0004549671,0.000660972,0.0003751277,0.0003353915],"domain_scores_gemma":[0.9983588,0.0002136715,0.0003097106,0.0004845817,0.0005486166,0.00008460411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001474072,0.0001250799,0.0003701256,0.00008996718,0.00001642361,1.952194e-7,0.001301859,0.00006111195,0.09022473,0.7506543,0.0003336926,0.1566751],"study_design_scores_gemma":[0.00008033933,0.0002464397,0.001010474,0.0002580432,0.00004426179,0.000001670933,0.00113319,0.5221568,0.2115051,0.2624236,0.0008494646,0.0002907132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03085725,0.00001896505,0.9487072,0.01532684,0.0004401445,0.0005914492,0.0000166438,0.000157123,0.003884428],"genre_scores_gemma":[0.9459001,0.000006714927,0.05295144,0.0007466443,0.00003013919,0.00002834943,0.000004030737,0.000008457938,0.0003241296],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9150429,"threshold_uncertainty_score":0.7051659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1181992600500137,"score_gpt":0.3626866063261057,"score_spread":0.244487346276092,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}