{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008102951,0.001369592,0.0008881619,0.02040582,0.0022845,0.00157937,0.001153007,0.001137671,0.01094689],"category_scores_gemma":[0.005943255,0.0004232884,0.0007033716,0.01095404,0.0006057994,0.002813993,0.002403265,0.000985998,0.007544285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008303373,"about_ca_system_score_gemma":0.003293239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00802828,"about_ca_topic_score_gemma":0.01721128,"domain_scores_codex":[0.9987717,0.00022729,0.0002691496,0.0003277132,0.0003036975,0.0001002812],"domain_scores_gemma":[0.9968395,0.001041335,0.0003708765,0.0004531118,0.001056953,0.0002381977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006309249,0.0005146243,0.01021044,0.009282473,0.0003097319,0.008461284,0.003621635,0.003045186,0.04631681,0.04161387,0.3803245,0.4956685],"study_design_scores_gemma":[0.00005063803,0.00008044467,0.01055573,0.001087106,0.0002360032,0.003265433,0.001398896,0.004300833,0.01710904,0.01167681,0.9500611,0.0001779364],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.09645796,0.01183965,0.212058,0.002461848,0.002410336,0.00213472,0.512271,0.02696649,0.1333999],"genre_scores_gemma":[0.1579242,0.003535358,0.3588827,0.0007065735,0.0003891729,0.001309309,0.4607089,0.002460731,0.01408294],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02040582,"threshold_uncertainty_score":0.03662103,"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."}}