{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001107263,0.0001808933,0.0002653246,0.008032052,0.002824458,0.004775007,0.0004378387,0.000297199,0.005475228],"category_scores_gemma":[0.003008933,0.0001632035,0.0001104725,0.01098266,0.007060398,0.006370427,0.002462073,0.0005692583,0.0005401408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005299511,"about_ca_system_score_gemma":0.006592326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1487775,"about_ca_topic_score_gemma":0.4388908,"domain_scores_codex":[0.9993005,0.0002757181,0.00006435854,0.00009353991,0.0001652403,0.0001007011],"domain_scores_gemma":[0.9984533,0.000826701,0.0002194753,0.0001372003,0.0002360641,0.0001273575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001520619,0.00003881007,0.0390999,0.001067213,0.00002185977,0.0009748052,0.1296029,0.0006728741,0.003655077,0.4915354,0.008478855,0.3247003],"study_design_scores_gemma":[0.00001171327,0.00003941187,0.07925751,0.00108181,0.00003354653,0.003269591,0.2676911,0.001474267,0.003096186,0.1412134,0.502762,0.00006950875],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6139761,0.02938919,0.04637732,0.0120993,0.0001445194,0.0001200072,0.001518096,0.0002367658,0.2961387],"genre_scores_gemma":[0.9422642,0.008878493,0.02826922,0.000533491,0.00003570637,0.00003689713,0.0006040355,0.00007259509,0.01930541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1487775,"threshold_uncertainty_score":0.2958231,"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."}}