{"id":"W4392367355","doi":"10.1162/coli_a_00512","title":"A Novel Alignment-based Approach for PARSEVAL Measuress","year":2023,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Parsing; Sentence; Natural language processing; Artificial intelligence; Lexical analysis; Parseval's theorem; Machine translation; Word (group theory); Linguistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000414872,0.0001364662,0.0001375059,0.0001574425,0.0001727696,0.0001564469,0.0006695569,0.00006674378,7.695515e-7],"category_scores_gemma":[0.001685288,0.0001340532,0.00006936133,0.0004732,0.0000430566,0.00003697828,0.0001261409,0.00009703215,0.000009307281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005304455,"about_ca_system_score_gemma":0.0001914315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003005405,"about_ca_topic_score_gemma":2.206609e-7,"domain_scores_codex":[0.9986968,0.0000202308,0.0002198167,0.0003561539,0.0004524512,0.0002545154],"domain_scores_gemma":[0.9984713,0.0004116724,0.0001003527,0.0002290198,0.0007172892,0.00007033479],"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":[0.00001534569,0.0001426484,0.00004954293,0.0001393208,0.00002484944,0.000008890592,0.0001464044,0.2022635,0.0004073539,0.7852108,0.006959952,0.004631341],"study_design_scores_gemma":[0.0003320258,0.00003182984,0.00003046138,0.00001832394,0.000007575174,0.000002778633,0.000003936443,0.89245,0.0009464008,0.1032599,0.002751252,0.0001655137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002482071,0.0001144454,0.9975126,0.0001660243,0.0004263354,0.0002561352,0.0000433665,0.001083693,0.0003725977],"genre_scores_gemma":[0.223503,2.894184e-7,0.7755782,0.0003372966,0.0002722031,0.00005546618,0.0001842056,0.00001435987,0.00005496935],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6901864,"threshold_uncertainty_score":0.5466533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05511895696161671,"score_gpt":0.3166822825463177,"score_spread":0.261563325584701,"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."}}