{"id":"W4318617465","doi":"10.1145/3582426","title":"A Dense Representation Framework for Lexical and Semantic Matching","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Representation (politics); Matching (statistics); Semantic matching; Lexical database; Information retrieval; WordNet; 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":[0.0002699711,0.00008937863,0.0001179099,0.0002586878,0.0002509021,0.0002984536,0.000242459,0.00007739756,0.000001242361],"category_scores_gemma":[0.0001243679,0.0000838851,0.00004808087,0.0005630975,0.00001741387,0.002336431,0.00001235699,0.0001160291,0.00006947175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002739213,"about_ca_system_score_gemma":0.00001648096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001866669,"about_ca_topic_score_gemma":5.444952e-7,"domain_scores_codex":[0.999169,0.00002966231,0.0003112138,0.0001355888,0.0001994683,0.0001550897],"domain_scores_gemma":[0.998891,0.0004464457,0.00009992628,0.0004150848,0.00009602516,0.00005155119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009970325,0.00004853284,0.0000718393,0.0005928349,0.0000773587,0.000004992972,0.01127096,0.01074227,0.0004186609,0.2491272,0.001172764,0.7263728],"study_design_scores_gemma":[0.0020597,0.000846112,0.002111976,0.001047826,0.00006343216,0.0002418818,0.006971666,0.4061319,0.03213847,0.505862,0.04126548,0.001259581],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002049779,0.00001531591,0.9957265,0.0005955267,0.000328906,0.0004885914,0.0000106396,0.0007039483,0.00008076194],"genre_scores_gemma":[0.861958,0.00009645316,0.1373112,0.0002280759,0.00003442107,0.0002509372,0.00001257327,0.000007627189,0.0001007052],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8599082,"threshold_uncertainty_score":0.3420735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04047221812486532,"score_gpt":0.3386158581131831,"score_spread":0.2981436399883178,"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."}}