{"id":"W4293576334","doi":"10.7557/12.6441","title":"Low hanging fruit and the Boasian trilogy in digital lexicography of morphologically rich languages","year":2022,"lang":"en","type":"article","venue":"Nordlyd","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Lexical database; Lexicon; Bilingual dictionary; Linguistics; Resource (disambiguation); Grammar; Artificial intelligence; Natural language processing; Word (group theory); Lexicography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004011294,0.0000828826,0.0001650274,0.0001894044,0.00009181038,0.00008052612,0.0007244538,0.00003038239,0.0000126933],"category_scores_gemma":[0.0001077038,0.00005667549,0.0000462438,0.0006415716,0.0001260854,0.0001498337,0.0006646232,0.0002137051,5.589633e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001411211,"about_ca_system_score_gemma":0.00002208895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004909738,"about_ca_topic_score_gemma":0.00001048516,"domain_scores_codex":[0.9991944,0.00007271692,0.0001597877,0.0002187901,0.0001856526,0.0001686956],"domain_scores_gemma":[0.9994773,0.0001345574,0.00008595818,0.000258133,0.00002341381,0.00002062871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003264587,0.0005105275,0.05458455,0.0001302588,0.00006467413,0.0006450529,0.01416432,0.00008343121,0.008971154,0.3184656,0.00139774,0.6006563],"study_design_scores_gemma":[0.01413669,0.003338848,0.05136571,0.0003250898,0.00006950622,0.001824092,0.006090734,0.01753011,0.04675377,0.8495494,0.006233434,0.002782579],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9155678,0.006949534,0.07115706,0.002538916,0.0001220973,0.0004296851,0.00001989888,0.0003309286,0.002884117],"genre_scores_gemma":[0.9778653,0.000005409844,0.02162983,0.000379534,0.00001327943,0.00003210235,0.000003215282,0.00000499482,0.00006635661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5978737,"threshold_uncertainty_score":0.231116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006440518135382094,"score_gpt":0.2418487025858582,"score_spread":0.2354081844504761,"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."}}