{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001429342,0.001017982,0.001296807,0.0026581,0.0005427002,0.00207318,0.002273988,0.001520061,0.005259689],"category_scores_gemma":[0.006192286,0.0005652129,0.001370637,0.003541874,0.00101094,0.005432134,0.002421117,0.0017407,0.002652319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001175376,"about_ca_system_score_gemma":0.001356866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007327286,"about_ca_topic_score_gemma":0.008302698,"domain_scores_codex":[0.9986361,0.0003845712,0.00009546386,0.0003233187,0.0004046883,0.0001559164],"domain_scores_gemma":[0.9987057,0.0004945679,0.0001264476,0.0003362515,0.0002822439,0.00005470921],"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":[0.0003521523,0.0003122949,0.001283565,0.0003869695,0.000169586,0.0002761532,0.0003603119,0.1627043,0.01771687,0.1289986,0.01438581,0.6730534],"study_design_scores_gemma":[0.00003472439,0.0001141761,0.0003570529,0.00003049386,0.00004188474,0.0002199353,0.00007716849,0.9040404,0.00393622,0.08395989,0.00715545,0.00003253896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00533668,0.000389841,0.9904472,0.0001689857,0.00004529574,0.00009216331,0.0003045884,0.001473504,0.001741841],"genre_scores_gemma":[0.3583828,0.001073272,0.6248046,0.0005992677,0.0002539236,0.0005826118,0.003392113,0.0005222003,0.01038927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007327286,"threshold_uncertainty_score":0.01759541,"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."}}