{"id":"W4285152239","doi":"10.18653/v1/2022.findings-acl.225","title":"Extracting Person Names from User Generated Text: Named-Entity Recognition for Combating Human Trafficking","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; Institut de Valorisation des Données; Canadian Institute for Advanced Research","keywords":"Computer science; Named-entity recognition; Punctuation; Natural language processing; Domain (mathematical analysis); Task (project management); Artificial intelligence; Grammar; Named entity; Information retrieval; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002072914,0.0001621509,0.0002465115,0.0001420009,0.002171615,0.0002129968,0.0006850574,0.00008834267,0.00005181324],"category_scores_gemma":[0.00725931,0.0001773106,0.0002619767,0.0004487335,0.00002051331,0.0001381733,0.000240201,0.0003534729,0.000003348149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005720556,"about_ca_system_score_gemma":0.0001520123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005117513,"about_ca_topic_score_gemma":0.000008948737,"domain_scores_codex":[0.9977863,0.0002356853,0.0005429546,0.0004009484,0.0007359872,0.000298126],"domain_scores_gemma":[0.9950731,0.002305043,0.001213347,0.0001671338,0.001194612,0.00004670422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002102162,0.0008247927,0.1374028,0.0002745581,0.001019629,0.000002584191,0.0139026,0.4114616,0.007283037,0.3954584,0.02431352,0.007846281],"study_design_scores_gemma":[0.001885789,0.0001684836,0.01823143,0.00007261396,0.0001351239,0.000001895561,0.0007752608,0.8964689,0.003433125,0.06324502,0.01505721,0.0005251674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5595523,0.0001022109,0.4275176,0.00150566,0.00596061,0.001515748,0.003060806,0.0002957034,0.0004893571],"genre_scores_gemma":[0.9440985,4.274596e-7,0.05318997,0.000217326,0.0003709945,0.00009717923,0.001492707,0.00002325087,0.000509593],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4850073,"threshold_uncertainty_score":0.9991274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04314776999712625,"score_gpt":0.2892943644149413,"score_spread":0.246146594417815,"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."}}