{"id":"W4360986317","doi":"","title":"Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2017co-located with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2017)","year":2017,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Knowledge extraction; Data science; Natural (archaeology); Information retrieval; Data mining; Geography; Archaeology","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":[0.02390772,0.001473199,0.002961092,0.002640727,0.00154056,0.01445335,0.003491249,0.003078756,0.02762648],"category_scores_gemma":[0.03387694,0.001179426,0.001900273,0.003204058,0.002371289,0.01289108,0.007710981,0.008442345,0.01058568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002211447,"about_ca_system_score_gemma":0.003915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002246589,"about_ca_topic_score_gemma":0.0032695,"domain_scores_codex":[0.9862502,0.007316921,0.001191498,0.00187089,0.002820732,0.0005497871],"domain_scores_gemma":[0.9625309,0.02062503,0.0006986431,0.006430631,0.006952852,0.0027619],"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":[0.0008430617,0.0007953946,0.00170559,0.001352066,0.0003750333,0.000451185,0.002585782,0.003692859,0.008610943,0.08481699,0.3474425,0.5473285],"study_design_scores_gemma":[0.000115117,0.0001585964,0.00140715,0.0006152971,0.0001600866,0.0005246788,0.0008668971,0.02923993,0.007782934,0.1384898,0.8205462,0.00009330551],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.01342026,0.03818107,0.809364,0.07181603,0.026106,0.00054043,0.003008045,0.00325511,0.03430903],"genre_scores_gemma":[0.1013098,0.02709399,0.6978237,0.009054223,0.0146091,0.0008293565,0.01549921,0.004416271,0.1293644],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.02762648,"threshold_uncertainty_score":0.1264376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05595412313270085,"score_gpt":0.322213632174657,"score_spread":0.2662595090419561,"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."}}