{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001330126,0.0002856063,0.0003248568,0.0008111393,0.0002115627,0.00134141,0.002941976,0.0002772408,0.000009683086],"category_scores_gemma":[0.0001635329,0.0002542521,0.00006304609,0.0003516434,0.0001552781,0.00471751,0.0009236688,0.0003822474,0.00002368346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006138313,"about_ca_system_score_gemma":0.0006036405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008501,"about_ca_topic_score_gemma":0.0002344457,"domain_scores_codex":[0.9974856,0.00002834781,0.0006376186,0.0008953721,0.0005368063,0.0004162046],"domain_scores_gemma":[0.9978606,0.0003310754,0.0004845677,0.0009699428,0.0002749308,0.00007886557],"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":[0.000003902667,0.00001148327,0.00009730952,0.00002967986,0.000001878872,0.000002661217,0.0003920279,0.003477717,0.0001990589,0.03812464,0.00000623684,0.9576534],"study_design_scores_gemma":[0.0004219609,0.00004593171,0.0009751594,0.0004583235,0.000002806035,0.00001897672,1.947508e-7,0.7878999,0.0003851143,0.2063266,0.003110528,0.0003544569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001462773,0.00005949563,0.9929087,0.0009384145,0.001947677,0.0009007434,0.000005321847,0.00007375529,0.003019596],"genre_scores_gemma":[0.2858499,0.00002537749,0.712539,0.0007410524,0.0003547479,0.0000806329,0.00001399692,0.00001916536,0.0003761357],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9572989,"threshold_uncertainty_score":0.999991,"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."}}