{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0124691,0.001852051,0.001684632,0.008922711,0.001489676,0.006395544,0.003358921,0.001710347,0.00350377],"category_scores_gemma":[0.06463953,0.0009641323,0.001411103,0.005906713,0.001942964,0.005739184,0.003608999,0.003224266,0.002086804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001896358,"about_ca_system_score_gemma":0.001968803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00167457,"about_ca_topic_score_gemma":0.001553168,"domain_scores_codex":[0.9777322,0.008279352,0.002496622,0.003024687,0.007912829,0.0005543766],"domain_scores_gemma":[0.9693965,0.01100757,0.002337451,0.006130014,0.01056578,0.0005626985],"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":[0.0003430912,0.000233144,0.006283846,0.0004260543,0.000276684,0.0001534232,0.0008340286,0.03747939,0.02726536,0.1748169,0.008157616,0.7437305],"study_design_scores_gemma":[0.00004753155,0.0003138505,0.003511581,0.0001393565,0.0001128999,0.0004589423,0.0001682673,0.7889706,0.03853088,0.1459067,0.0216522,0.0001872009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003035631,0.00009625126,0.993215,0.00005673958,0.00004187143,0.00007835103,0.0001180456,0.002500813,0.0008572582],"genre_scores_gemma":[0.07486638,0.00005804887,0.9228679,0.00005621077,0.0000668062,0.0003044022,0.0003279857,0.00095135,0.0005009735],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0124691,"threshold_uncertainty_score":0.06594366,"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."}}