{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001195485,0.0007048884,0.0004314801,0.001900272,0.0004867804,0.0007049469,0.000770372,0.001146048,0.001621314],"category_scores_gemma":[0.003513259,0.0001556598,0.0004675522,0.001226919,0.0005181276,0.002551274,0.0009705076,0.0007263892,0.003418523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003101302,"about_ca_system_score_gemma":0.0004459386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001148711,"about_ca_topic_score_gemma":0.001878166,"domain_scores_codex":[0.9989896,0.000358493,0.0001060096,0.000289632,0.0001985506,0.00005774136],"domain_scores_gemma":[0.9975261,0.001245781,0.0003123847,0.0004803909,0.0003699767,0.00006538915],"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":[0.0005261494,0.0003688666,0.01103248,0.0008043283,0.0001106126,0.001679569,0.0007570369,0.01711802,0.04668313,0.003431828,0.04797442,0.8695135],"study_design_scores_gemma":[0.00007034902,0.0003652453,0.02153688,0.000169986,0.0001838781,0.003633951,0.001630623,0.6872189,0.1754163,0.01143346,0.09819223,0.0001481315],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3759468,0.004301409,0.5652753,0.002622926,0.00114382,0.0005189169,0.01332812,0.02530907,0.01155362],"genre_scores_gemma":[0.608487,0.001702283,0.3499383,0.0006134751,0.0003343271,0.0001859225,0.02847566,0.0004663651,0.009796586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001900272,"threshold_uncertainty_score":0.006322443,"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."}}