{"id":"W3016027609","doi":"10.5281/zenodo.3629884","title":"TEI Lex-0 In Action: Improving the Encoding of the Dictionary of the Academia das Ciências de Lisboa","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Linguistic Association","funders":"Fundação para a Ciência e a Tecnologia; Horizon 2020 Framework Programme; Universidade Nova de Lisboa; European Commission","keywords":"Encoding (memory); Computer science; Context (archaeology); Natural language processing; Interoperability; Artificial intelligence; Information retrieval; World Wide Web; History","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":[0.00152255,0.000625841,0.0006643609,0.001630519,0.0007513464,0.003444282,0.001008886,0.0007848679,0.009835473],"category_scores_gemma":[0.009345046,0.0004925914,0.0005980589,0.002672011,0.0009951565,0.004358848,0.0027854,0.001732414,0.003587851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002389204,"about_ca_system_score_gemma":0.00308902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006555666,"about_ca_topic_score_gemma":0.007675377,"domain_scores_codex":[0.9985305,0.0004215972,0.0002342005,0.0002832728,0.0003948266,0.0001355265],"domain_scores_gemma":[0.9937302,0.00208723,0.0003895721,0.001875163,0.00167364,0.0002441846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002835431,0.0004456623,0.0074461,0.002389629,0.00008459165,0.001211331,0.009278175,0.01412121,0.05757737,0.1736316,0.05388732,0.6770916],"study_design_scores_gemma":[0.0002612648,0.0005066428,0.003594286,0.0005821253,0.0001128102,0.001590413,0.003111064,0.08432673,0.1628084,0.03595754,0.7068966,0.0002520009],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1621661,0.001065427,0.7147448,0.002543909,0.001131257,0.0007314059,0.0171334,0.04569118,0.05479256],"genre_scores_gemma":[0.3644733,0.000706877,0.5785978,0.000553406,0.00006647411,0.0003650422,0.02472354,0.01171809,0.01879541],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009835473,"threshold_uncertainty_score":0.03290296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02575874479289359,"score_gpt":0.2688100019633009,"score_spread":0.2430512571704073,"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."}}