{"id":"W2020278455","doi":"10.1075/li.30.1.03nad","title":"A survey of named entity recognition and classification","year":2007,"lang":"en","type":"article","venue":"Lingvisticae Investigationes","topic":"Topic Modeling","field":"Computer Science","cited_by":2488,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Natural Environment Research Council; Alfred P. Sloan Foundation","keywords":"Computer science; Natural language processing; Matching (statistics); Artificial intelligence; Field (mathematics); Information retrieval; Named entity; Key (lock); Word (group theory); Linguistics; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.007817268,0.001834114,0.003062243,0.01431008,0.001421953,0.004739904,0.003972962,0.002092465,0.008388628],"category_scores_gemma":[0.01780604,0.0008817977,0.001803512,0.02716402,0.0008828376,0.01703105,0.002152723,0.00199369,0.009767558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001537826,"about_ca_system_score_gemma":0.003004159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003658784,"about_ca_topic_score_gemma":0.002882272,"domain_scores_codex":[0.9927514,0.001778281,0.000977919,0.001259781,0.002921331,0.0003113784],"domain_scores_gemma":[0.983254,0.008957142,0.000813954,0.001887972,0.004719707,0.0003672986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005454073,0.0000934599,0.002592209,0.00291345,0.00009142201,0.0001106906,0.0001230192,0.001602677,0.0006050287,0.009097715,0.05034482,0.9323709],"study_design_scores_gemma":[0.00001528499,0.0001294233,0.004572304,0.001812747,0.0001558987,0.001274415,0.0005029165,0.01744683,0.003408942,0.01920094,0.9513692,0.0001112916],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.006312263,0.6061504,0.3328271,0.007809829,0.002659225,0.0005552437,0.006302957,0.005685422,0.03169764],"genre_scores_gemma":[0.03708992,0.679804,0.2334854,0.003396826,0.004006412,0.0005703187,0.02437643,0.0008212925,0.01644936],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01431008,"threshold_uncertainty_score":0.04134214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1391236913969597,"score_gpt":0.291564756940622,"score_spread":0.1524410655436623,"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."}}