{"id":"W2002977992","doi":"10.1075/term.19.1.07ber","title":"Review of Andersen (2012): Exploring Newspaper Language: Using the web to create and investigate a large corpus of modern Norwegian","year":2013,"lang":"en","type":"article","venue":"Terminology International Journal of Theoretical and Applied Issues in Specialized Communication","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Norwegian; Newspaper; Computer science; Web page; Linguistics; Corpus linguistics; World Wide Web; Natural language processing; Media studies; Sociology; Philosophy","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":[0.006254961,0.0009742675,0.00136482,0.01741824,0.001060356,0.003305885,0.001286411,0.001173392,0.005990957],"category_scores_gemma":[0.02013853,0.0005451886,0.0005173664,0.02122658,0.00268204,0.005107935,0.002589303,0.001806931,0.005288822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002501208,"about_ca_system_score_gemma":0.006332176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02373279,"about_ca_topic_score_gemma":0.06132232,"domain_scores_codex":[0.9977763,0.0008177735,0.0003070592,0.0003070958,0.0007123712,0.0000792643],"domain_scores_gemma":[0.9819782,0.01197275,0.0006984989,0.0005159592,0.004303943,0.0005305734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006004125,0.00003890117,0.001711683,0.02739883,0.0001575036,0.0002299092,0.002626757,0.0002827882,0.001096297,0.008215229,0.2774282,0.6807539],"study_design_scores_gemma":[0.000004170861,0.00001513989,0.004591147,0.009979937,0.00007805117,0.0002411792,0.0007725129,0.00004545297,0.0002727662,0.001261967,0.9827116,0.0000261318],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"commentary","genre_scores_codex":[0.0005162345,0.9824835,0.001949845,0.007139131,0.001545892,0.00004715944,0.000875763,0.00004891443,0.005393518],"genre_scores_gemma":[0.00395251,0.9833929,0.003587774,0.003188723,0.001021051,0.0001024392,0.001295332,0.00008143768,0.003377846],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.02373279,"threshold_uncertainty_score":0.0471893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02705234104219418,"score_gpt":0.3215060213513493,"score_spread":0.2944536803091551,"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."}}