{"id":"W3173999950","doi":"10.1609/aaai.v35i16.17654","title":"On Scalar Embedding of Relative Positions in Attention Models","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Beijing Advanced Innovation Center for Big Data and Brain Computing; Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment; National Natural Science Foundation of China","keywords":"Embedding; Computer science; Probabilistic logic; Encoding (memory); Scalar (mathematics); Artificial intelligence; Transformer; Heuristic; Pattern recognition (psychology); Algorithm; 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":[0.00159807,0.0007296983,0.0006426689,0.0007803533,0.000341597,0.001084625,0.001391857,0.0008912083,0.003506762],"category_scores_gemma":[0.009150921,0.0004995331,0.0006533649,0.00115235,0.001305464,0.005171562,0.002579364,0.002021189,0.0005621055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00125679,"about_ca_system_score_gemma":0.0007593474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003440479,"about_ca_topic_score_gemma":0.003093276,"domain_scores_codex":[0.9991026,0.0003881055,0.00005619324,0.0002324933,0.0001398133,0.0000808476],"domain_scores_gemma":[0.9977075,0.001269462,0.0002089192,0.00047487,0.0002328016,0.0001063829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003141121,0.00007714035,0.001603415,0.000172163,0.00005418017,0.0001227341,0.0004663032,0.3527237,0.005541526,0.3799602,0.003191081,0.2557734],"study_design_scores_gemma":[0.00001327008,0.00004805242,0.0002320205,0.000013322,0.00001053809,0.00003527539,0.00002247173,0.8345512,0.001036238,0.1629224,0.001101979,0.00001322574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02028938,0.0003243318,0.9767573,0.0003620677,0.00003531176,0.00002354072,0.0001335993,0.0005269207,0.001547604],"genre_scores_gemma":[0.7916178,0.0008855307,0.2016508,0.0003025667,0.0001532486,0.0001173018,0.000461235,0.0002117178,0.004599785],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003506762,"threshold_uncertainty_score":0.01173127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08892781869382743,"score_gpt":0.3121096265494795,"score_spread":0.2231818078556521,"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."}}