{"id":"W1996527383","doi":"10.7202/038312ar","title":"Is Bigger Better? Corpus and Dictionary Use in the Search for Compounds, Collocations, Derived Forms and Fixed Expressions","year":2009,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Bilingual dictionary; Corpus linguistics; Machine-readable dictionary; Speech recognition","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0002914722,0.0001235774,0.0001810581,0.0001498773,0.001194495,0.0004388657,0.00009783172,0.00002248179,0.00004544222],"category_scores_gemma":[0.00002554372,0.00006831398,0.0001061369,0.00006636091,0.0003438638,0.0004539186,0.00001182159,0.000188984,3.467431e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008319216,"about_ca_system_score_gemma":0.00001182182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004752048,"about_ca_topic_score_gemma":0.0002101476,"domain_scores_codex":[0.9992371,0.0001001214,0.0002005829,0.0001269708,0.0001429323,0.0001923607],"domain_scores_gemma":[0.9994574,0.00025793,0.00005559321,0.00009203579,0.00008358996,0.00005347625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0007017701,0.00140724,0.04302606,0.0002388903,0.00339207,0.0001444783,0.5569357,0.00001727055,0.01010899,0.1459954,0.04777262,0.1902596],"study_design_scores_gemma":[0.002919383,0.0009345101,0.5592667,0.0002006935,0.0011488,0.0005318813,0.03158764,0.00007519686,0.0009217181,0.05834351,0.3434635,0.0006064035],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9685877,0.02682086,0.0002284019,0.003707409,0.0001179428,0.0002448506,0.00006233018,0.00001349136,0.0002169964],"genre_scores_gemma":[0.9907561,0.006638396,0.0005499949,0.001605456,0.0001968823,0.000026035,0.000007889523,0.000008173231,0.0002111003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.525348,"threshold_uncertainty_score":0.9187211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08673062436678199,"score_gpt":0.2818169938120741,"score_spread":0.1950863694452922,"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."}}