{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003741625,0.0001003862,0.000107864,0.0001226544,0.0003019069,0.0001832331,0.0004042314,0.00005728715,0.00004093811],"category_scores_gemma":[0.0000368748,0.00009660716,0.00008315001,0.0002346715,0.000007385686,0.0004919132,0.00005973068,0.00008771899,0.0000611119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004121599,"about_ca_system_score_gemma":0.00002255826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004544726,"about_ca_topic_score_gemma":0.00002298703,"domain_scores_codex":[0.9989308,0.0000223555,0.0001709236,0.000377768,0.000184893,0.0003133205],"domain_scores_gemma":[0.9994369,0.0001194292,0.00004426593,0.0003015098,0.00004457689,0.00005328752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009043695,0.0001039609,0.0007549456,0.000206949,0.00005967314,0.00003581176,0.01820395,0.01909222,0.1831795,0.2465533,0.01135562,0.520445],"study_design_scores_gemma":[0.0002335474,0.00003523004,0.0005925142,0.00002041387,0.000003342269,0.000004336648,0.0004197145,0.9929234,0.00264263,0.0008263238,0.002163077,0.0001354132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2707953,0.00001308649,0.7238709,0.001118457,0.000369537,0.0001779003,6.530202e-7,0.0009254708,0.002728764],"genre_scores_gemma":[0.9446028,0.00000129998,0.05300567,0.0001263869,0.0002052553,0.00002984772,0.00000712114,0.00001259972,0.002009035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9738312,"threshold_uncertainty_score":0.3939526,"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."}}