{"id":"W2070720620","doi":"10.4312/ala.4.2.37-51","title":"Construction of a Learner Corpus for Japanese Language Learners: Natane and Nutmeg","year":2014,"lang":"en","type":"article","venue":"Acta Linguistica Asiatica","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Tellabs (Canada)","funders":"Ministry of Education, Culture, Sports, Science and Technology","keywords":"Nutmeg; Computer science; Identification (biology); Register (sociolinguistics); Variety (cybernetics); Collocation (remote sensing); Natural language processing; Reading (process); Active listening; Linguistics; Artificial intelligence; World Wide Web; Psychology; Communication; Biology; Medicine; Traditional medicine","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":[0.003808579,0.000866731,0.0008459178,0.003761675,0.001954971,0.001390002,0.001182593,0.001098691,0.01537689],"category_scores_gemma":[0.01155921,0.0007388963,0.0004310182,0.002278378,0.001261341,0.002507658,0.004894949,0.00165348,0.006657595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007598132,"about_ca_system_score_gemma":0.002680717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005930942,"about_ca_topic_score_gemma":0.01377301,"domain_scores_codex":[0.9976022,0.0008530713,0.0003746861,0.0006239183,0.0004131579,0.0001329565],"domain_scores_gemma":[0.9882612,0.004426135,0.0004171949,0.00217497,0.004096621,0.0006239639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002121102,0.003012978,0.07767586,0.006221422,0.000162654,0.005905152,0.07717669,0.003894534,0.1534845,0.009025595,0.1165802,0.5447392],"study_design_scores_gemma":[0.0007386831,0.001230113,0.1998366,0.0009864835,0.000284915,0.005413601,0.04302177,0.0211189,0.08414271,0.003371627,0.6394783,0.0003763447],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8019567,0.000780465,0.07643241,0.0007693699,0.0005035676,0.006377821,0.07319432,0.006366994,0.03361838],"genre_scores_gemma":[0.5076801,0.0005130644,0.2516327,0.0004450254,0.0001208765,0.01252825,0.2016109,0.003248216,0.0222208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01537689,"threshold_uncertainty_score":0.05144083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007812596003544454,"score_gpt":0.2621353032343071,"score_spread":0.2543227072307627,"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."}}