{"id":"W4385572313","doi":"10.18653/v1/2023.sustainlp-1.22","title":"Small Character Models Match Large Word Models for Autocomplete Under Memory Constraints","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Character (mathematics); Computer science; Simple (philosophy); Word (group theory); Natural language processing; Natural (archaeology); Natural language; Speech recognition; Arithmetic; Artificial intelligence; Linguistics; Mathematics; History; Philosophy; Epistemology; Archaeology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005918384,0.0002118225,0.0002709001,0.0001643797,0.0001596792,0.0001880921,0.0009671733,0.000108486,0.00007160783],"category_scores_gemma":[0.00000883442,0.0001953924,0.0001367434,0.0002889537,0.00003942351,0.0007326865,0.000466581,0.0001415346,0.0001756583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004592942,"about_ca_system_score_gemma":0.0001033814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002320178,"about_ca_topic_score_gemma":0.00002453405,"domain_scores_codex":[0.997947,0.00003820956,0.0003644923,0.0006578064,0.0002652213,0.0007272467],"domain_scores_gemma":[0.9987323,0.0001546385,0.00007306823,0.0007855136,0.0001087204,0.0001457136],"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":[0.000003944684,0.00003037985,0.000004307641,0.00003046133,0.0000274375,0.000007056692,0.0007042817,0.07625021,0.0002270943,0.8997039,0.001060452,0.02195048],"study_design_scores_gemma":[0.0004184509,0.000009250721,0.00003854915,0.00001370301,0.000003712614,0.00000500035,0.00006458813,0.7192231,0.0000990644,0.2795908,0.000348909,0.0001848963],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008018288,0.000009516685,0.9797234,0.002853118,0.0004384372,0.000729043,0.00002192103,0.001012201,0.007194095],"genre_scores_gemma":[0.6736003,0.000005480244,0.3151655,0.003065701,0.0001558492,0.0002508115,0.00002104322,0.00003665523,0.007698595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6655821,"threshold_uncertainty_score":0.796787,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.143643382113694,"score_gpt":0.2830863677551433,"score_spread":0.1394429856414494,"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."}}