{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001878295,0.001237405,0.001666785,0.001364555,0.001158244,0.003217695,0.001737329,0.001853351,0.01229673],"category_scores_gemma":[0.01321053,0.00118324,0.001877715,0.001366884,0.0008371617,0.008094921,0.002558778,0.003029027,0.008367707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008927913,"about_ca_system_score_gemma":0.00160006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006270898,"about_ca_topic_score_gemma":0.01698487,"domain_scores_codex":[0.9981853,0.0006103474,0.0001740147,0.0005822015,0.0002553787,0.0001928194],"domain_scores_gemma":[0.9874773,0.008726018,0.0003605174,0.002198284,0.0009186825,0.000319185],"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":[0.001968808,0.0005642993,0.004699753,0.001115933,0.0004021325,0.001289696,0.001381365,0.249224,0.02303179,0.07869282,0.07573289,0.5618966],"study_design_scores_gemma":[0.00005817736,0.00006550558,0.0004889897,0.00004440444,0.00004689073,0.0002210149,0.000184351,0.9117998,0.00383374,0.07709706,0.006132387,0.00002768612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07702219,0.001638567,0.9000472,0.001618378,0.0002877839,0.0002358777,0.003899258,0.006703288,0.008547418],"genre_scores_gemma":[0.576622,0.001364483,0.3754401,0.0006988176,0.0005350974,0.000367441,0.02397869,0.003582229,0.01741112],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01229673,"threshold_uncertainty_score":0.04113668,"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."}}