{"id":"W4401768891","doi":"10.18280/isi.290402","title":"Enhancing Spatial Information Extraction from Arabic Text: A Hybrid Approach with Ontology and Rule-Based","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Ontology; Arabic; Computer science; Rule-based system; Information extraction; Information retrieval; Natural language processing; Extraction (chemistry); Artificial intelligence; Data mining; Linguistics; Chromatography; Chemistry","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":[0.001790594,0.001042873,0.001050316,0.00713304,0.0009289149,0.003073975,0.001425364,0.0009608993,0.002261995],"category_scores_gemma":[0.004803532,0.000470865,0.001565887,0.004368011,0.000810212,0.003750169,0.001830567,0.001017952,0.001866469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006841749,"about_ca_system_score_gemma":0.001774966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006405745,"about_ca_topic_score_gemma":0.008588742,"domain_scores_codex":[0.9975814,0.0005389896,0.0004102231,0.0005038123,0.0008720726,0.00009352845],"domain_scores_gemma":[0.996929,0.001319148,0.000255123,0.0003522647,0.00105608,0.00008841974],"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":[0.0001693209,0.0004998613,0.004772447,0.001098725,0.0003428047,0.0009299883,0.001696336,0.008539675,0.05004136,0.008118391,0.00733745,0.9164536],"study_design_scores_gemma":[0.000144478,0.0003672102,0.01389669,0.0005729775,0.0009606367,0.002169133,0.0044742,0.6837651,0.1340604,0.03319354,0.1260439,0.0003518242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02971716,0.0005673685,0.956979,0.0006124501,0.0000971694,0.0007110628,0.001123229,0.004812676,0.005379986],"genre_scores_gemma":[0.07602812,0.0004246985,0.9185023,0.0002057423,0.00005135014,0.0003247028,0.001787508,0.0001685207,0.00250714],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00713304,"threshold_uncertainty_score":0.01273692,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01089918752678037,"score_gpt":0.2425444160809753,"score_spread":0.2316452285541949,"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."}}