{"id":"W4389519833","doi":"10.18653/v1/2023.findings-emnlp.219","title":"SWEET - Weakly Supervised Person Name Extraction for Fighting Human Trafficking","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Samsung; Canadian Institute for Advanced Research","keywords":"Benchmark (surveying); Pipeline (software); Computer science; Generalizability theory; Matching (statistics); Domain (mathematical analysis); Task (project management); Artificial intelligence; Labeled data; Sequence labeling; Machine learning; Data mining; Natural language processing; Mathematics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001343871,0.001614267,0.001072667,0.001959428,0.0009676869,0.001158464,0.001549661,0.001484016,0.003707693],"category_scores_gemma":[0.003806951,0.0004603739,0.001071807,0.001106983,0.0008822192,0.00304977,0.001982292,0.001669105,0.007528955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000424618,"about_ca_system_score_gemma":0.001454024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003585273,"about_ca_topic_score_gemma":0.00923162,"domain_scores_codex":[0.9984889,0.0003967139,0.0000827137,0.0005842901,0.0003078296,0.0001395712],"domain_scores_gemma":[0.9981802,0.0006143,0.0001872109,0.0005694728,0.0003635529,0.00008538407],"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":[0.0006690409,0.0005578077,0.01082805,0.0005298842,0.0002247337,0.0007544623,0.0007177925,0.02595223,0.04983069,0.009348482,0.08198445,0.8186024],"study_design_scores_gemma":[0.00006645602,0.0002265813,0.005302997,0.0001037074,0.0001267346,0.001143066,0.0006087999,0.8497077,0.05345301,0.02211094,0.06706232,0.00008782064],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0578277,0.001042592,0.8984702,0.00066692,0.000261901,0.0002802525,0.003565613,0.02969152,0.008193216],"genre_scores_gemma":[0.3184471,0.0005576527,0.6186494,0.001051778,0.0003332759,0.000402373,0.03110875,0.001752393,0.02769723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003707693,"threshold_uncertainty_score":0.01240349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07735140164470757,"score_gpt":0.3088931297072098,"score_spread":0.2315417280625022,"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."}}