{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001773548,0.001462838,0.001152612,0.002436071,0.0005171024,0.001282437,0.002081888,0.001174433,0.004010779],"category_scores_gemma":[0.005580677,0.0004191708,0.000835909,0.002402836,0.0003696367,0.00460742,0.001703997,0.001679476,0.004396183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006726512,"about_ca_system_score_gemma":0.0006316391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00464859,"about_ca_topic_score_gemma":0.008465516,"domain_scores_codex":[0.9986855,0.0003582745,0.0001417432,0.000443657,0.0002484378,0.0001222265],"domain_scores_gemma":[0.9981026,0.0007070721,0.0001469632,0.0005590068,0.0004322052,0.00005229515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005856959,0.0004905936,0.003633881,0.0004424146,0.0002162041,0.0002579855,0.0001291553,0.08316369,0.02514764,0.007649493,0.04655562,0.8317277],"study_design_scores_gemma":[0.00004295548,0.00008838942,0.001215774,0.00002981015,0.00005988604,0.00007562439,0.00005376573,0.9671366,0.01113948,0.01228934,0.00783738,0.00003105046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1327824,0.004893999,0.8130838,0.001131773,0.0006781577,0.0002036438,0.008169241,0.03273203,0.006324942],"genre_scores_gemma":[0.6286769,0.001014341,0.3239325,0.0003152336,0.0003242835,0.0002944791,0.03577311,0.0008270648,0.008842105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00464859,"threshold_uncertainty_score":0.01341736,"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."}}