{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003437254,0.00005983563,0.00006748402,0.00002712245,0.00006709217,0.0001033027,0.0001286043,0.0000307348,0.00003445593],"category_scores_gemma":[0.0000874877,0.0000552583,0.00001735654,0.0001315891,0.00001136007,0.0002536369,0.00007543446,0.00005758767,0.0000185798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000156371,"about_ca_system_score_gemma":0.00001502799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005652949,"about_ca_topic_score_gemma":0.000009597738,"domain_scores_codex":[0.9992036,0.00006135352,0.0001061497,0.0002325241,0.0003018308,0.00009458626],"domain_scores_gemma":[0.9996731,0.00002562371,0.00005315464,0.0001277741,0.00005892515,0.00006148344],"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":[0.00001829869,0.0000242168,0.004570398,0.00006380134,0.0000230842,0.00001125043,0.1579848,0.004076305,0.004772296,0.003455207,0.0005018791,0.8244985],"study_design_scores_gemma":[0.0003184131,0.00003811624,0.0106132,0.000009058193,0.00001554691,0.000001819004,0.001153165,0.986012,0.000358137,0.0004524738,0.000940656,0.00008744989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8502939,0.0009109493,0.1459836,0.001428636,0.00006635437,0.0001451807,9.831158e-7,0.00007449655,0.001095952],"genre_scores_gemma":[0.9928231,0.00001317477,0.006473535,0.0004231156,0.0002162129,0.000008212893,0.000006243842,0.000003279214,0.00003309222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9819357,"threshold_uncertainty_score":0.2253368,"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."}}