{"id":"W831928984","doi":"","title":"Exploiting a Multilingual Web-based Encyclopedia for Bilingual Terminology Extraction","year":2010,"lang":"en","type":"article","venue":"Institutional Repositories DataBase (IRDB)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Terminology; Encyclopedia; Natural language processing; Rank (graph theory); Information retrieval; Exploit; Artificial intelligence; Ontology; Filter (signal processing); Term (time); Information extraction; World Wide Web; Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004835795,0.0002749719,0.0002240772,0.0002381499,0.0007271127,0.000298082,0.0009260707,0.0002186222,0.000008052776],"category_scores_gemma":[0.002485914,0.0002592229,0.0001097673,0.0003210324,0.0002913788,0.001777324,0.0002743927,0.0006046237,0.000009553536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001106838,"about_ca_system_score_gemma":0.001642764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001254833,"about_ca_topic_score_gemma":0.0001660525,"domain_scores_codex":[0.9978161,0.00004583117,0.0004878748,0.0007617868,0.0004548296,0.0004335418],"domain_scores_gemma":[0.9977599,0.00053486,0.0002643185,0.0007980907,0.0005020695,0.0001407702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001293314,0.0003028811,0.001374275,0.0001664724,0.00002942151,0.0004648344,0.000276545,0.00004382866,0.6379238,0.30175,0.0007380254,0.05680063],"study_design_scores_gemma":[0.001450473,0.0001878801,0.0002218171,0.0002194538,0.00004167444,0.001100638,0.00005388719,0.03634838,0.8168166,0.005101965,0.1375652,0.0008920472],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2509674,0.0003893464,0.7374435,0.0004338135,0.007605965,0.0005639917,0.0001845082,0.001618185,0.0007933462],"genre_scores_gemma":[0.477558,0.000004351374,0.5208089,0.0001366064,0.001114563,0.0001118054,0.0001647136,0.00001339621,0.00008764327],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.296648,"threshold_uncertainty_score":0.999986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01890596775989091,"score_gpt":0.3136890455180256,"score_spread":0.2947830777581347,"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."}}