{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002954629,0.001655061,0.002009255,0.002240707,0.001301895,0.00155115,0.003058676,0.001683813,0.003821549],"category_scores_gemma":[0.008417856,0.0006834607,0.001504537,0.003094909,0.0007537381,0.003805452,0.001712602,0.003787952,0.002798276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009476267,"about_ca_system_score_gemma":0.001869441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005178457,"about_ca_topic_score_gemma":0.01169701,"domain_scores_codex":[0.99815,0.0005575393,0.0001178969,0.000630568,0.0003791504,0.0001649155],"domain_scores_gemma":[0.9945458,0.002971208,0.0002551228,0.001178168,0.0008788112,0.0001708756],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001790843,0.0001980039,0.002693037,0.0001882907,0.0003005149,0.0001192949,0.0002509287,0.1765452,0.008494018,0.0144393,0.01715038,0.779442],"study_design_scores_gemma":[0.00001140542,0.00003515627,0.000452782,0.00001374741,0.0000353069,0.00005747476,0.00003101362,0.9741096,0.002917039,0.01994087,0.002376807,0.00001873223],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01012051,0.0005628435,0.9818119,0.0001618062,0.00009594459,0.00005783295,0.0003152166,0.005957887,0.0009160262],"genre_scores_gemma":[0.1593657,0.0004407497,0.8321614,0.0002468447,0.0002345304,0.0002730116,0.003511905,0.001351005,0.002414858],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005178457,"threshold_uncertainty_score":0.01562577,"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."}}