{"id":"W1999506550","doi":"10.1075/term.10.1.12dro","title":"Review of Jackson & Moulinier (2002): Natural language processing for online applications: Text retrieval, extraction and categorization","year":2004,"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":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Categorization; Natural language processing; Computer science; Artificial intelligence; Keyword extraction; Information retrieval; Linguistics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006042907,0.0001213793,0.0002984859,0.0002143145,0.0000548476,0.00005733582,0.0008352213,0.000110706,0.00001194363],"category_scores_gemma":[0.000368348,0.0001021653,0.00004217414,0.0001877128,0.0003443763,0.0003292761,0.0001975123,0.0002987804,6.11204e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007968996,"about_ca_system_score_gemma":0.00005385896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005808604,"about_ca_topic_score_gemma":0.000004158876,"domain_scores_codex":[0.9987787,0.00007202555,0.0006485278,0.0001758531,0.00021402,0.000110858],"domain_scores_gemma":[0.9983793,0.00018394,0.0006218502,0.0002589173,0.0005219236,0.00003409381],"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":[0.0002232145,0.0001887307,0.00001204884,0.000349882,0.00002417183,0.000001782851,0.000810291,0.000003755669,0.00859303,0.662283,0.00006670216,0.3274434],"study_design_scores_gemma":[0.002741863,0.0001628214,0.0002316174,0.004019951,0.00007720895,0.00040588,0.0002316131,0.001072694,0.0315794,0.9501515,0.008970291,0.0003551348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02157633,0.3350776,0.6189859,0.02254716,0.0002373135,0.001044302,0.00001455413,0.0001018759,0.0004150263],"genre_scores_gemma":[0.5622795,0.02989268,0.4069502,0.0006505536,0.0001410908,0.00002063846,0.00004165868,0.000009035321,0.00001458862],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5407032,"threshold_uncertainty_score":0.4166178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01488603802225284,"score_gpt":0.3623013151247689,"score_spread":0.3474152771025161,"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."}}