{"id":"W2250317589","doi":"10.63317/5oexzp4sjvme","title":"Improving Entity Linking using Surface Form Refinement","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Polytechnique Montréal","funders":"","keywords":"Entity linking; Computer science; Rewriting; Natural language processing; Context (archaeology); NIST; Annotation; Task (project management); Word (group theory); Matching (statistics); Information retrieval; Artificial intelligence; Knowledge base; Similarity (geometry); Process (computing); Named entity; Linguistics; Programming language; Mathematics","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":[0.007947532,0.00009638659,0.0001684689,0.00008869218,0.0002315378,0.0005364104,0.0006691803,0.00003547873,0.0007918316],"category_scores_gemma":[0.0009635821,0.00006991119,0.0000688902,0.0003085389,0.00003407076,0.0005842993,0.00069726,0.00007360525,0.0004134732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004653284,"about_ca_system_score_gemma":0.00001999606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009360363,"about_ca_topic_score_gemma":0.0006093039,"domain_scores_codex":[0.9976609,0.0001293799,0.0005031075,0.000403383,0.00104694,0.0002562705],"domain_scores_gemma":[0.9985459,0.0003304318,0.0001895886,0.0007462042,0.000113375,0.0000744597],"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":[0.00002035261,0.000160479,0.00751666,0.00005726723,0.00003362439,0.000003394402,0.0006436428,0.001943136,0.007175549,0.2605816,0.01530359,0.7065607],"study_design_scores_gemma":[0.0006253381,0.00008629761,0.002366496,0.00003218536,0.00003084507,0.000001990654,0.001488653,0.2716252,0.003535239,0.06747489,0.6523055,0.0004273464],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2608907,0.00001083626,0.6994624,0.0005648006,0.0005069338,0.0001253145,0.000004522843,0.00006420694,0.03837026],"genre_scores_gemma":[0.9417626,0.00000253207,0.05035804,0.001216881,0.00009498955,0.000001163551,0.000006887123,0.000006968354,0.006549938],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7061334,"threshold_uncertainty_score":0.867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2097279930675458,"score_gpt":0.4123134049304373,"score_spread":0.2025854118628914,"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."}}