{"id":"W4402671274","doi":"10.18653/v1/2024.acl-long.808","title":"Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing","year":2024,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"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; Computer science; Tree (set theory); Ensemble learning; Artificial intelligence; Algorithm; Machine learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001827792,0.0001457652,0.0001412274,0.0002127389,0.0001484748,0.0006788558,0.0005821745,0.000063438,0.00003208024],"category_scores_gemma":[0.00004077607,0.0001184891,0.0001020447,0.0004255295,0.00007720679,0.0005753505,0.00007717776,0.00008988026,0.00005657629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004209922,"about_ca_system_score_gemma":0.0001320224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001265449,"about_ca_topic_score_gemma":0.000005975403,"domain_scores_codex":[0.9988397,0.00001622459,0.0002282077,0.0004652688,0.000161091,0.0002895413],"domain_scores_gemma":[0.9992039,0.0002281386,0.00003038201,0.0004393939,0.00004872125,0.00004943074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001986892,0.00002308173,0.00005946876,0.00003139838,0.00001132009,0.000008679811,0.00009270318,0.00001432306,0.003033131,0.389963,0.003068398,0.6036925],"study_design_scores_gemma":[0.0006407652,0.00009373049,0.0001025179,0.0001180896,0.00001744675,0.000009471501,0.0002134116,0.8556584,0.05540476,0.03515739,0.05219094,0.0003930613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009916015,0.0004642953,0.9799111,0.009349567,0.0006941318,0.0002947548,0.000003790512,0.002502067,0.005788699],"genre_scores_gemma":[0.7716318,0.00001007199,0.2266013,0.0002633251,0.00004058588,0.00008757296,0.00000785336,0.00001079553,0.001346654],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8556441,"threshold_uncertainty_score":0.6546222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03995286326179818,"score_gpt":0.2922784025302487,"score_spread":0.2523255392684505,"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."}}