{"id":"W2807583563","doi":"10.48550/arxiv.1806.03489","title":"Robust Lexical Features for Improved Neural Network Named-Entity Recognition","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Named-entity recognition; Word (group theory); Artificial intelligence; Matching (statistics); Representation (politics); Feature vector; Feature (linguistics); Natural language processing; Artificial neural network; Entity linking; Recurrent neural network; Pattern recognition (psychology); Knowledge base; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003314023,0.0003024259,0.0003202716,0.0001180684,0.000273832,0.0002205209,0.001558243,0.0004226665,0.00002059264],"category_scores_gemma":[0.00006455681,0.0003494714,0.0002935561,0.000276881,0.0001010209,0.000402979,0.001662874,0.0005829705,0.00002682393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001625486,"about_ca_system_score_gemma":0.0001346137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001245916,"about_ca_topic_score_gemma":0.0001367362,"domain_scores_codex":[0.9977803,0.0001144811,0.0002096653,0.00131675,0.00007225473,0.0005065483],"domain_scores_gemma":[0.9981394,0.0001118955,0.0002388093,0.001066517,0.0002745385,0.0001688343],"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":[0.0002481504,0.0001977178,0.001255195,0.0002809766,0.0002549463,0.00009558184,0.0002471655,0.9011643,0.00005466873,0.06139287,0.01177786,0.02303055],"study_design_scores_gemma":[0.0004008823,0.00006645579,0.000404861,0.0000608962,0.0000554306,0.000004234741,0.000008154315,0.8967662,0.00003788378,0.1014041,0.000421641,0.0003692031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1049639,0.00004792737,0.8909526,0.0002384645,0.002358679,0.0005196197,0.00002421464,0.0003039297,0.0005906961],"genre_scores_gemma":[0.9449611,0.00004424501,0.05231033,0.0003092513,0.001154189,0.000004103455,0.00006996693,0.00002370879,0.001123073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8399972,"threshold_uncertainty_score":0.9998958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1321239846210392,"score_gpt":0.200364422793399,"score_spread":0.06824043817235981,"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."}}