{"id":"W3153895709","doi":"10.18653/v1/2021.eacl-srw.21","title":"TMR: Evaluating NER Recall on Tough Mentions","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Computer science; Recall; Natural language processing; Linguistics; Philosophy","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01127938,0.002054104,0.001459083,0.009425928,0.0008767295,0.002825708,0.001927489,0.00216642,0.002215579],"category_scores_gemma":[0.028086,0.0004462456,0.001116539,0.004761313,0.0009486606,0.004378107,0.001883813,0.001141666,0.002701927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007392082,"about_ca_system_score_gemma":0.0006411612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006209582,"about_ca_topic_score_gemma":0.01049065,"domain_scores_codex":[0.9927239,0.001934228,0.001038618,0.001869809,0.002044754,0.0003887597],"domain_scores_gemma":[0.9814317,0.009691283,0.001743609,0.002997426,0.003808508,0.000327402],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001374131,0.000532524,0.1508185,0.00204392,0.001925029,0.0006325387,0.002597418,0.05527863,0.03989586,0.00515013,0.04378991,0.6959613],"study_design_scores_gemma":[0.000240627,0.002095019,0.2151821,0.000467743,0.001508898,0.003392872,0.002422832,0.5561141,0.1607288,0.01436369,0.04272251,0.0007609046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6429636,0.007086534,0.282017,0.000836933,0.0006788746,0.0005027804,0.01211965,0.02464282,0.02915185],"genre_scores_gemma":[0.8622268,0.0008952431,0.1065521,0.0002351176,0.0002784347,0.0002693589,0.01933645,0.001528725,0.008677726],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9887206,"threshold_uncertainty_score":0.05965173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1072639897763181,"score_gpt":0.3539379442665714,"score_spread":0.2466739544902533,"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."}}