{"id":"W2251013081","doi":"10.63317/4i8tgm5asdq4","title":"A disambiguation resource extracted from Wikipedia for semantic annotation","year":2012,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Entity linking; Information retrieval; Task (project management); Annotation; Natural language processing; Ontology; Word (group theory); Resource (disambiguation); Point (geometry); Artificial intelligence; Relation (database); Semantic annotation; Knowledge base; Linguistics; Data mining","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":[0.0002195922,0.00008150056,0.00007668376,0.00006053457,0.00007056221,0.0001113553,0.0003087951,0.00006159644,0.00001059958],"category_scores_gemma":[0.0001790937,0.00006810414,0.00003037931,0.0001908845,0.00001192779,0.001091624,0.00005920199,0.00006316123,0.00001364084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002761674,"about_ca_system_score_gemma":0.00001384551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006285065,"about_ca_topic_score_gemma":0.000008099702,"domain_scores_codex":[0.9993023,0.00002808751,0.0001373347,0.000178321,0.0001547118,0.0001992761],"domain_scores_gemma":[0.9993598,0.0001863659,0.00007856705,0.0002532098,0.00006771642,0.00005438184],"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":[0.00003690475,0.0002380662,0.003343482,0.00005671015,0.0000258922,0.000001908021,0.006548335,0.000003710597,0.09235703,0.1594949,0.01601829,0.7218748],"study_design_scores_gemma":[0.001397921,0.000206066,0.03286211,0.0001610612,0.00007994879,0.00001833181,0.0002603349,0.2106025,0.4057222,0.319312,0.0280342,0.001343409],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0239019,0.0006616067,0.9733661,0.0007003793,0.000123328,0.0002007128,0.000003068839,0.0007199299,0.0003229755],"genre_scores_gemma":[0.5164828,8.460893e-7,0.482929,0.0002342443,0.0001253226,0.0000221858,0.00002869114,0.000005034744,0.0001719154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7205314,"threshold_uncertainty_score":0.2777206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01916484537813383,"score_gpt":0.285825939011608,"score_spread":0.2666610936334742,"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."}}