{"id":"W3015648683","doi":"10.18653/v1/2021.eacl-main.246","title":"ProFormer: Towards On-Device LSH Projection Based Transformers","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Memory footprint; Computer science; Embedding; Computation; Projection (relational algebra); Precomputation; Mobile device; Dimension (graph theory); Transformer; Word embedding; Theoretical computer science; Artificial intelligence; Speech recognition; Algorithm; Mathematics; Programming language; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004135536,0.0003348726,0.0003321263,0.0002146826,0.0001032933,0.0004212396,0.0009653732,0.000316071,0.00009985632],"category_scores_gemma":[0.00002932513,0.000298766,0.0002486286,0.0002954771,0.00001993054,0.0003010715,0.0003570495,0.0007263242,0.0000264715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002220887,"about_ca_system_score_gemma":0.001391516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005122078,"about_ca_topic_score_gemma":0.0001155399,"domain_scores_codex":[0.9974157,0.0000836849,0.0004041479,0.001084534,0.0006192281,0.0003927404],"domain_scores_gemma":[0.9986036,0.00003329812,0.000113054,0.00095846,0.0001830652,0.0001084792],"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":[0.00002168415,0.0003111669,0.0001782514,0.0009806332,0.0001114074,0.00004099436,0.00233078,0.006746935,0.0002964957,0.01252062,0.0005501889,0.9759108],"study_design_scores_gemma":[0.000370887,0.0000960963,0.0003212728,0.0003019041,0.00001999039,0.00000755784,0.0001472376,0.9850813,0.00974473,0.0008065006,0.002522317,0.0005802055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01455614,0.00003090332,0.9358594,0.003685798,0.001733782,0.0007662021,0.00000280431,0.0005087543,0.04285622],"genre_scores_gemma":[0.6815341,0.00003264025,0.3139269,0.002479899,0.0002385412,0.0002929528,0.00003971293,0.00003369745,0.001421631],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9783344,"threshold_uncertainty_score":0.9999465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04861438386620129,"score_gpt":0.2893038014633784,"score_spread":0.2406894175971771,"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."}}