{"id":"W2997919746","doi":"10.1609/aaai.v34i05.6304","title":"Leveraging Multi-Token Entities in Document-Level Named Entity Recognition","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Fundamental Research Funds for the Central Universities; Renmin University of China; National Natural Science Foundation of China","keywords":"Security token; Computer science; Context (archaeology); Sentence; Task (project management); Natural language processing; Artificial intelligence; Named-entity recognition; Relevance (law); Annotation; Process (computing); Entity linking; Information retrieval; Knowledge base; Programming language","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":[0.002219649,0.001174008,0.00122925,0.003139296,0.0006760248,0.001470468,0.001846488,0.001499543,0.002040342],"category_scores_gemma":[0.004254309,0.0004143128,0.001341505,0.002951437,0.0006367065,0.007075618,0.001746957,0.001780435,0.002602368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006700845,"about_ca_system_score_gemma":0.0006846286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004103184,"about_ca_topic_score_gemma":0.008044108,"domain_scores_codex":[0.9986469,0.0002637231,0.0001467505,0.0006271023,0.0002041387,0.0001113423],"domain_scores_gemma":[0.9975339,0.00108781,0.0002704829,0.0005628554,0.0004507277,0.00009423119],"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":[0.0007873148,0.0003471312,0.008835184,0.0007454527,0.0003664531,0.001366695,0.0005929323,0.03980731,0.06177334,0.01030858,0.02010895,0.8549606],"study_design_scores_gemma":[0.00005103833,0.0003034041,0.009817806,0.0001410267,0.0005723107,0.001825912,0.0003064707,0.8239563,0.08247399,0.03040989,0.04992615,0.0002158408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04137243,0.002909439,0.9400608,0.000539826,0.0003483315,0.0002190364,0.001903519,0.008688387,0.003958192],"genre_scores_gemma":[0.4930029,0.00182022,0.4846482,0.000533133,0.0003178289,0.0001669443,0.01012171,0.0005129897,0.008876036],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004103184,"threshold_uncertainty_score":0.01173878,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.24879956231443,"score_gpt":0.3083061023145282,"score_spread":0.05950654000009811,"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."}}