{"id":"W2729052508","doi":"10.1111/coin.12120","title":"From French Wikipedia to Erudit: A test case for cross‐domain open information extraction","year":2017,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Classifier (UML); Pipeline (software); Information extraction; Entity linking; Information retrieval; Open domain; Domain (mathematical analysis); Natural language processing; Task (project management); Artificial intelligence; Named-entity recognition; Precision and recall; Question answering; Knowledge base; Mathematics; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003879769,0.0001371463,0.0001372342,0.00008897043,0.0007581273,0.002511546,0.001949213,0.00006453392,0.00002885044],"category_scores_gemma":[0.0007916206,0.0001464129,0.00004815132,0.00009221332,0.00004748587,0.003783117,0.0007076523,0.0001055618,0.0002315441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009142874,"about_ca_system_score_gemma":0.0001437884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001163215,"about_ca_topic_score_gemma":0.000122389,"domain_scores_codex":[0.9987212,0.00001920564,0.0004186908,0.0003761001,0.0002542895,0.000210536],"domain_scores_gemma":[0.9977964,0.0006722561,0.000283544,0.0006823459,0.0004317457,0.000133686],"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":[0.00002450844,0.0001139155,0.001948641,0.00002780849,0.00002648995,0.000099782,0.005680714,0.4217655,0.00007009559,0.0785963,0.004057541,0.4875887],"study_design_scores_gemma":[0.000150889,0.00005822076,0.004907923,0.00002898348,0.000003145538,0.0001098928,0.00006495398,0.7937128,0.0003843601,0.1946621,0.005717405,0.0001993532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03126625,0.00001203803,0.9647953,0.001513936,0.0008932475,0.0005802934,0.00007603879,0.00006390868,0.0007990137],"genre_scores_gemma":[0.5717735,6.860363e-7,0.4275386,0.0003312985,0.0001785305,0.00007406966,0.00002419172,0.000004083094,0.00007498797],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5405073,"threshold_uncertainty_score":0.998524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07660808466055637,"score_gpt":0.3909621699752346,"score_spread":0.3143540853146783,"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."}}