{"id":"W6948033462","doi":"10.48448/qtzj-ed53","title":"Extracting Person Names from User Generated Text: Named-Entity Recognition for Combating Human Trafficking","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Domain (mathematical analysis); Human trafficking; Keyword extraction; The Internet; Key (lock); Domain knowledge","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":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002677322,0.0006921236,0.0006826771,0.001554036,0.002637036,0.0009180226,0.001319391,0.0003325921,0.0126489],"category_scores_gemma":[0.001254302,0.0007574633,0.000200379,0.001845396,0.0008518942,0.0008189222,0.0002860501,0.001010711,0.0004547903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001034468,"about_ca_system_score_gemma":0.0006425672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00298917,"about_ca_topic_score_gemma":0.005972136,"domain_scores_codex":[0.994363,0.0002573484,0.0006837666,0.001884936,0.001663393,0.001147527],"domain_scores_gemma":[0.996735,0.0003824682,0.001508441,0.0007205036,0.0004032474,0.0002503477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001224417,0.001697835,0.006024441,0.0004450339,0.0006176289,0.00008604107,0.007123158,0.00209942,0.4299361,0.0009357597,0.3794363,0.1714759],"study_design_scores_gemma":[0.008068813,0.0009676057,0.001452835,0.00269471,0.001300472,0.00007930693,0.03406893,0.426556,0.009638582,0.001431595,0.5058324,0.007908656],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6718505,0.002149473,0.009487817,0.0004598056,0.007430964,0.008496447,0.01166585,0.008321619,0.2801375],"genre_scores_gemma":[0.6349267,0.00003340004,0.1874077,0.0006883032,0.004473456,0.0007687316,0.02003554,0.005303927,0.1463622],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4244566,"threshold_uncertainty_score":0.9994876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07787218548081365,"score_gpt":0.327766534767591,"score_spread":0.2498943492867773,"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."}}