{"id":"W4200314022","doi":"10.1145/3487057","title":"Joined Type Length Encoding for Nested Named Entity Recognition","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Named-entity recognition; Encoding (memory); Leverage (statistics); Artificial intelligence; Sequence (biology); Pattern recognition (psychology); Natural language processing; Task (project management); Genetics","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":[0.0001961659,0.0001250345,0.0001268139,0.000172418,0.0003781751,0.000453935,0.0002162442,0.00008559749,0.00003519871],"category_scores_gemma":[0.0001623967,0.0001286444,0.00004960792,0.0003933467,0.00001881185,0.001761918,0.00001430018,0.0001665255,0.0000166337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004080317,"about_ca_system_score_gemma":0.00009435091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006834156,"about_ca_topic_score_gemma":0.00001240461,"domain_scores_codex":[0.9990836,0.00003559755,0.0003025291,0.0001970583,0.0001815382,0.0001997266],"domain_scores_gemma":[0.9992535,0.00006248552,0.0001204518,0.0003122326,0.0001714935,0.00007980039],"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":[0.00001597155,0.00002724789,0.000005512353,0.000168835,0.000009934038,0.000002507132,0.0119927,0.0003035526,0.0007823846,0.00007902901,0.00001525233,0.9865971],"study_design_scores_gemma":[0.004518568,0.0002425705,0.0004311197,0.001210264,0.0001214,0.0003021982,0.0367815,0.8544968,0.08098397,0.002109878,0.01748868,0.001313085],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04065474,0.00008539183,0.9555414,0.001223147,0.0001367177,0.0001847479,0.000009403246,0.0002248984,0.001939491],"genre_scores_gemma":[0.9260691,0.00001196289,0.07249438,0.001090574,0.00004818619,0.00002640916,0.00006592532,0.000009279493,0.0001842269],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.985284,"threshold_uncertainty_score":0.5245965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01810936799937288,"score_gpt":0.2498349065838877,"score_spread":0.2317255385845149,"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."}}