{"id":"W2469016277","doi":"10.1007/978-3-319-34111-8_20","title":"Harnessing Open Information Extraction for Entity Classification in a French Corpus","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Open domain; Information extraction; Domain (mathematical analysis); Precision and recall; Information retrieval; Natural language processing; Recall; Named-entity recognition; Relationship extraction; Artificial intelligence; Entity linking; Question answering; Knowledge base; Task (project management); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003221625,0.001486681,0.001021697,0.007031884,0.002600294,0.003879739,0.001121687,0.001272931,0.006897293],"category_scores_gemma":[0.01149376,0.0006982044,0.001193682,0.005052744,0.001046394,0.005197991,0.002973139,0.001751195,0.004890334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001883805,"about_ca_system_score_gemma":0.003096869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03338187,"about_ca_topic_score_gemma":0.04120931,"domain_scores_codex":[0.9970288,0.00110096,0.0002990953,0.0008675885,0.000491617,0.0002120974],"domain_scores_gemma":[0.9893923,0.006673234,0.0002987908,0.001247832,0.002188748,0.0001992011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005678035,0.000277318,0.007654846,0.00179539,0.0002402374,0.001762371,0.004158619,0.008143332,0.04054119,0.02272411,0.1096199,0.802515],"study_design_scores_gemma":[0.0002018231,0.0002889312,0.03485516,0.0007629046,0.0006869328,0.00255461,0.004620643,0.1628809,0.07624926,0.04015419,0.6763362,0.0004083141],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2182459,0.01565027,0.6094315,0.006291649,0.002488177,0.0007997962,0.07285876,0.02939799,0.04483592],"genre_scores_gemma":[0.3881439,0.003855381,0.3988937,0.00064665,0.001048792,0.0007487406,0.1859009,0.003192823,0.01756915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03338187,"threshold_uncertainty_score":0.06637514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0454656989705401,"score_gpt":0.2937363488754873,"score_spread":0.2482706499049472,"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."}}