{"id":"W4392425987","doi":"10.48550/arxiv.2403.00143","title":"Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Alberta Innovates; DeepMind; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Parsing; Tree (set theory); Computer science; Artificial intelligence; Ensemble learning; Natural language processing; Machine learning; Mathematics; Combinatorics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023409,0.0004010113,0.0003975663,0.0005350139,0.0002397428,0.0004842462,0.001913786,0.000327659,0.00001470495],"category_scores_gemma":[0.00005220361,0.0004359164,0.0003394434,0.0006763955,0.0002111915,0.0003071292,0.001408311,0.000531544,0.00007311913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002271317,"about_ca_system_score_gemma":0.0004255814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005092353,"about_ca_topic_score_gemma":0.00002089204,"domain_scores_codex":[0.9976283,0.00006039839,0.0002939869,0.00143952,0.0001125397,0.0004653099],"domain_scores_gemma":[0.9979916,0.0002062969,0.0002122505,0.00132157,0.0001527453,0.0001155685],"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":[0.00003136265,0.000131366,0.0004019249,0.0003450368,0.0001396068,0.0002478846,0.0002261203,0.01472304,0.0004449403,0.9244916,0.001570506,0.05724663],"study_design_scores_gemma":[0.0007291346,0.00005347637,0.00006444948,0.000269192,0.000109244,0.000002801373,0.000175817,0.7866096,0.002263961,0.2068414,0.002289192,0.0005917214],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02126542,0.0002703831,0.9704233,0.001682286,0.00134258,0.0006683033,0.00003819707,0.001768288,0.002541203],"genre_scores_gemma":[0.9767781,0.00006540737,0.02141444,0.00009836287,0.00006105772,0.00001174498,0.0000387099,0.00002664933,0.001505474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9555127,"threshold_uncertainty_score":0.9998093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1041477433313896,"score_gpt":0.2212843106027825,"score_spread":0.1171365672713929,"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."}}