{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003685506,0.0001367428,0.0002201928,0.0001541386,0.00009085114,0.00008200672,0.0008454116,0.00007836169,0.00002143742],"category_scores_gemma":[0.0003207015,0.0001174179,0.0001060593,0.0006946872,0.0001005156,0.0005837509,0.0002726015,0.000281407,0.00001513855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005931369,"about_ca_system_score_gemma":0.00009499663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002889639,"about_ca_topic_score_gemma":0.00001035977,"domain_scores_codex":[0.9983932,0.0000273957,0.0005326843,0.0004223107,0.0004087654,0.000215594],"domain_scores_gemma":[0.9986697,0.0001131995,0.0002779888,0.0002804962,0.0006153131,0.00004323508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001383767,0.000132235,0.00008785241,0.00002012067,0.000006844398,7.735632e-7,0.001083544,0.006166717,0.03712082,0.9466375,0.000006439562,0.00872332],"study_design_scores_gemma":[0.00001577279,0.00004472786,0.0001004581,0.0003478789,0.000003704824,0.000001677825,0.000246479,0.4180312,0.1579714,0.4231682,7.20224e-7,0.00006775257],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5475321,0.00002325875,0.4356866,0.003020421,0.0002472858,0.0002335579,0.000003700533,0.00003810683,0.01321503],"genre_scores_gemma":[0.9890391,0.00001837657,0.0107048,0.0000871324,0.00001620314,0.0000117444,4.238674e-7,0.000006490383,0.0001157618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5234693,"threshold_uncertainty_score":0.4788162,"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."}}