{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004351441,0.0001928981,0.0002394584,0.0001214687,0.0001181772,0.0003082778,0.00161007,0.00007212385,0.0000739305],"category_scores_gemma":[0.0004815212,0.0001682903,0.00009207448,0.0005354744,0.0001126735,0.0007833692,0.0004997496,0.0003446715,0.00010109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006529487,"about_ca_system_score_gemma":0.00008249094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001704326,"about_ca_topic_score_gemma":0.00003048887,"domain_scores_codex":[0.9980869,0.00002567684,0.0005767677,0.0005382863,0.0004441371,0.0003281841],"domain_scores_gemma":[0.9990373,0.00005302062,0.0002770819,0.0001966259,0.0003422846,0.00009364079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001209098,0.0003320655,0.004745659,0.0002794524,0.0000396318,0.000004437419,0.03177736,0.0005605086,0.07775555,0.4945555,0.0001316473,0.3896973],"study_design_scores_gemma":[0.00009641772,0.00008972857,0.0006125756,0.0003361855,0.000009013851,0.000002328367,0.001830974,0.4278571,0.4473074,0.121475,0.00005452182,0.0003288109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6668225,0.00003136615,0.3187821,0.009777927,0.0006015523,0.0006133748,0.000006633624,0.0001620088,0.003202555],"genre_scores_gemma":[0.9828137,0.00003323769,0.01644209,0.0005314452,0.00006047098,0.00002436102,6.594346e-7,0.000009024788,0.00008499334],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4272966,"threshold_uncertainty_score":0.6862679,"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."}}