{"id":"W3159500995","doi":"","title":"Multi-Task Transfer Learning for Fine-Grained Named Entity Recognition.","year":2019,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Task (project management); Transfer of learning; Transfer (computing); Named-entity recognition; Natural language processing; Artificial intelligence; Parallel computing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003703219,0.0012447,0.001314639,0.002318247,0.001127958,0.001458753,0.003286433,0.002349517,0.004867424],"category_scores_gemma":[0.009867026,0.0004917586,0.001266519,0.002758067,0.0007745561,0.005339063,0.00330225,0.003099975,0.003649122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001031022,"about_ca_system_score_gemma":0.001451228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006255192,"about_ca_topic_score_gemma":0.00710878,"domain_scores_codex":[0.9981955,0.0007036693,0.0001253485,0.0005205262,0.0002131964,0.0002418252],"domain_scores_gemma":[0.9955465,0.002374355,0.0002222564,0.00108649,0.0005559828,0.0002143449],"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":[0.000581185,0.00070323,0.002330385,0.0004263996,0.000342523,0.0002605276,0.0003091971,0.07408594,0.008252854,0.01097048,0.04093763,0.8607996],"study_design_scores_gemma":[0.0000307167,0.0001181912,0.001315583,0.00002906605,0.00006589288,0.00008453093,0.0001682545,0.9375982,0.005549445,0.04930393,0.005702488,0.00003363467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03829663,0.004159312,0.9407243,0.001266859,0.000656278,0.0002448671,0.001779623,0.008677009,0.004195111],"genre_scores_gemma":[0.7429107,0.001237493,0.2334939,0.000661993,0.0006814091,0.0005994096,0.008930402,0.0003709101,0.01111368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006255192,"threshold_uncertainty_score":0.01958472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0168385891176107,"score_gpt":0.2481488195242912,"score_spread":0.2313102304066804,"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."}}