{"id":"W3050298219","doi":"10.1007/978-3-030-55814-7_2","title":"Extraction of a Knowledge Graph from French Cultural Heritage Documents","year":2020,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Cultural heritage; Knowledge graph; Information extraction; Graph; Christian ministry; Relationship extraction; Knowledge extraction; Information retrieval; Context (archaeology); World Wide Web; Natural language processing; Artificial intelligence; Geography; Archaeology; Political science","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":[0.0001887978,0.0009147406,0.0006273453,0.008083963,0.001037103,0.001689718,0.0006590874,0.0009185405,0.004599318],"category_scores_gemma":[0.001177349,0.0004009024,0.001027031,0.00516999,0.0003542739,0.001183161,0.0006064479,0.0005665125,0.002404055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001043958,"about_ca_system_score_gemma":0.001979954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03496833,"about_ca_topic_score_gemma":0.04447922,"domain_scores_codex":[0.9997527,0.00003616626,0.00002292658,0.00009245618,0.0000688779,0.00002687053],"domain_scores_gemma":[0.9994578,0.0002934299,0.00003570255,0.00005175607,0.0001325854,0.00002873287],"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":[0.0003017644,0.0002934471,0.00587198,0.001612926,0.0002482383,0.003689269,0.001092535,0.01020104,0.05118223,0.01549851,0.04834198,0.8616662],"study_design_scores_gemma":[0.0001709822,0.0004732051,0.04715594,0.001258443,0.001563533,0.006323657,0.003200555,0.2533482,0.1211288,0.04756227,0.5176004,0.0002139097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2476904,0.008299039,0.5944307,0.002789323,0.0004987797,0.001213993,0.06788064,0.02716357,0.05003363],"genre_scores_gemma":[0.3267307,0.004275267,0.5554861,0.0003346123,0.0001489261,0.0002692514,0.09076196,0.0009293812,0.02106384],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03496833,"threshold_uncertainty_score":0.06952953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03249528905846527,"score_gpt":0.3237258388079702,"score_spread":0.2912305497495049,"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."}}