{"id":"W7024784001","doi":"","title":"A study of similarity measures for natural language processing as applied to candidate-project matching","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Matching (statistics); Similarity (geometry); Pattern recognition (psychology); Natural language; Measure (data warehouse); Similarity measure","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01308508,0.0003987101,0.00119813,0.006310351,0.001158231,0.003813193,0.001757575,0.001405837,0.002283111],"category_scores_gemma":[0.1103155,0.0003409437,0.001003747,0.008322627,0.001640604,0.007489784,0.001695206,0.001236367,0.0004340326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001478296,"about_ca_system_score_gemma":0.001183253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0024319,"about_ca_topic_score_gemma":0.001548955,"domain_scores_codex":[0.9873173,0.006520231,0.001321327,0.001500068,0.002941933,0.0003991787],"domain_scores_gemma":[0.7971984,0.1830771,0.00523755,0.006513011,0.00682981,0.001144242],"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":[0.001928185,0.0009025847,0.05118936,0.001215267,0.0005374031,0.0004553885,0.002300088,0.05918659,0.0218748,0.1896624,0.004182788,0.6665651],"study_design_scores_gemma":[0.0001025375,0.001136635,0.02223344,0.0001143663,0.0002211042,0.001080426,0.001349361,0.856865,0.01269284,0.09981896,0.00430423,0.00008089456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3876526,0.00379957,0.6021084,0.0005017265,0.000123645,0.0002504735,0.0003782805,0.0005750107,0.004610229],"genre_scores_gemma":[0.8363487,0.0006416085,0.1608004,0.00006569246,0.0001361861,0.0001526353,0.00075838,0.0001447503,0.0009516608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01308508,"threshold_uncertainty_score":0.06920135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02633078822008934,"score_gpt":0.2985178834296658,"score_spread":0.2721870952095765,"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."}}