{"id":"W2179519966","doi":"10.1162/tacl_a_00104","title":"Named Entity Recognition with Bidirectional LSTM-CNNs","year":2016,"lang":"en","type":"preprint","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Feature engineering; Feature (linguistics); Word (group theory); Artificial intelligence; Lexicon; Named-entity recognition; Task (project management); Natural language processing; Encoding (memory); State (computer science); Architecture; Entity linking; Deep learning; Knowledge base","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":[],"consensus_categories":[],"category_scores_codex":[0.0004917182,0.0002052072,0.0002742988,0.000159353,0.0003289576,0.0001020883,0.0006733891,0.0002312499,0.000009888337],"category_scores_gemma":[0.000863964,0.0001621611,0.0002943136,0.000218486,0.00004399561,0.00007342455,0.0000729962,0.0003373063,0.000006957234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005519709,"about_ca_system_score_gemma":0.0005932096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003785249,"about_ca_topic_score_gemma":0.00003338543,"domain_scores_codex":[0.9979836,0.000106825,0.0005223708,0.000420194,0.0007569281,0.0002100508],"domain_scores_gemma":[0.9950942,0.0009232767,0.0009036153,0.0004040382,0.002623569,0.0000512341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007398837,0.0004107382,0.002493157,0.0003372116,0.0009733625,5.661178e-7,0.0005099511,0.8986678,0.00003352467,0.08651488,0.0009340167,0.009050834],"study_design_scores_gemma":[0.001135755,0.00008062233,0.002624327,0.0003635176,0.000288257,0.000003764626,0.00001117642,0.4125876,0.0006234305,0.577189,0.004629223,0.000463219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001055956,0.00002158433,0.9913074,0.001027224,0.003814213,0.0005396473,0.0008144261,0.0001377583,0.001281817],"genre_scores_gemma":[0.7926186,0.000007765815,0.2055044,0.00007299522,0.0005195515,0.000100538,0.0001081085,0.00002337927,0.001044683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7915626,"threshold_uncertainty_score":0.6612738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02717742762268828,"score_gpt":0.2607877003144704,"score_spread":0.2336102726917821,"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."}}