{"id":"W1989001126","doi":"10.3115/1220355.1220502","title":"Fast computation of lexical affinity models","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Computation; Scalability; Terabyte; Independence (probability theory); Artificial intelligence; Parametric statistics; Similarity (geometry); Focus (optics); Natural language processing; Theoretical computer science; Algorithm; Mathematics; Database","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":[0.001907023,0.001001306,0.001575312,0.002440965,0.001138745,0.002769832,0.002459312,0.001804698,0.006719669],"category_scores_gemma":[0.01627198,0.001217514,0.001272939,0.002546169,0.0007292145,0.006175927,0.004087914,0.002481436,0.003554702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001177254,"about_ca_system_score_gemma":0.001893989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005358063,"about_ca_topic_score_gemma":0.008709565,"domain_scores_codex":[0.9980054,0.000482282,0.0001302523,0.0004096852,0.0007788868,0.0001933706],"domain_scores_gemma":[0.9956205,0.002401899,0.0002405889,0.0008820199,0.0006936311,0.0001612986],"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":[0.0004562503,0.0002018529,0.00439289,0.0004070381,0.0002153044,0.0004347652,0.0005978282,0.2650185,0.01665009,0.1232168,0.01265514,0.5757536],"study_design_scores_gemma":[0.00002126378,0.00002513453,0.0003545301,0.00001002739,0.00001583187,0.00008941439,0.00005236507,0.8916491,0.002796914,0.1018188,0.003143187,0.00002350772],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009211029,0.0001341347,0.9873854,0.00008927397,0.00002386211,0.00003810094,0.000182668,0.001985371,0.0009501084],"genre_scores_gemma":[0.2478109,0.0002767197,0.745422,0.0001373876,0.00008513967,0.0003353063,0.001590468,0.0008167062,0.003525393],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006719669,"threshold_uncertainty_score":0.02247959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02419785949263349,"score_gpt":0.2846610855098097,"score_spread":0.2604632260171763,"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."}}