{"id":"W3031043157","doi":"","title":"WEXEA: Wikipedia EXhaustive Entity Annotation","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Annotation; Hyperlink; Information retrieval; Entity linking; Named-entity recognition; Relationship extraction; Natural language processing; Task (project management); Publication; Information extraction; Named entity; Relation (database); Artificial intelligence; World Wide Web; Web page; Knowledge base; Database","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":[0.009988223,0.003635436,0.002159588,0.01348401,0.003863646,0.004511585,0.003977229,0.002954405,0.02507942],"category_scores_gemma":[0.03560342,0.001270972,0.001926575,0.006931653,0.001198937,0.00945017,0.008674054,0.002844961,0.01761478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001459771,"about_ca_system_score_gemma":0.005224796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03309637,"about_ca_topic_score_gemma":0.04394478,"domain_scores_codex":[0.9860215,0.005578929,0.001630083,0.002650826,0.003257885,0.0008607636],"domain_scores_gemma":[0.9679819,0.01457781,0.000956546,0.007211316,0.00730128,0.001971079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002646182,0.001844655,0.01007355,0.005221295,0.001330604,0.0008505665,0.001307947,0.006505875,0.01190307,0.005157434,0.6825647,0.2705941],"study_design_scores_gemma":[0.002505266,0.002188492,0.03467909,0.002272159,0.002242471,0.002854786,0.004811017,0.1830381,0.07998212,0.02203852,0.6624891,0.0008989591],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.1237874,0.006735745,0.1369563,0.002288386,0.003138864,0.005723819,0.4786192,0.198221,0.04452935],"genre_scores_gemma":[0.1139518,0.001046636,0.1327395,0.0007503279,0.0002369355,0.003116468,0.7258298,0.008416058,0.01391254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03309637,"threshold_uncertainty_score":0.08389902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0339419726941602,"score_gpt":0.2878343625034358,"score_spread":0.2538923898092756,"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."}}