{"id":"W2100703320","doi":"10.1109/wi.2007.132","title":"Enhancing Search Engine Quality Using Concept-based Text Retrieval","year":2007,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sentence; Computer science; Natural language processing; Phrase; Representation (politics); Semantics (computer science); Term (time); Artificial intelligence; Text graph; Search engine indexing; Information retrieval; Text 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":[0.002571329,0.0001045275,0.0001736508,0.0001578174,0.0001404048,0.0001404873,0.0005751226,0.00005303883,0.0000974517],"category_scores_gemma":[0.0001572528,0.00009239504,0.00007830689,0.0009164038,0.00004683606,0.0002902097,0.0001519672,0.0001439692,0.00004721919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006439948,"about_ca_system_score_gemma":0.0001317549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004360707,"about_ca_topic_score_gemma":0.00004587622,"domain_scores_codex":[0.998425,0.00008786721,0.000313728,0.0003661627,0.0004280639,0.0003791785],"domain_scores_gemma":[0.998758,0.0003389659,0.00005510887,0.0006027165,0.000110282,0.0001349788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009785789,0.0004571574,0.009196439,0.0001123237,0.0002120393,0.0001996233,0.004052301,0.01311899,0.7482908,0.04265519,0.0008455853,0.1807616],"study_design_scores_gemma":[0.0003690409,0.00004387443,0.001946045,0.00002549209,0.00001076518,0.000004286721,0.0002576019,0.3779011,0.6186318,0.00003778405,0.0005017291,0.0002704415],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2213165,0.00002954613,0.7775214,0.0001674869,0.00007622454,0.00002666566,0.000002274865,0.0001247118,0.0007351776],"genre_scores_gemma":[0.8027864,3.986382e-7,0.1965489,0.0002698702,0.00007581489,9.935651e-8,0.00000589243,0.00000466401,0.0003080001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5814698,"threshold_uncertainty_score":0.376776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05747550079097764,"score_gpt":0.3511540425861295,"score_spread":0.2936785417951519,"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."}}