{"id":"W4385570721","doi":"10.18653/v1/2023.findings-acl.625","title":"EmbedTextNet: Dimension Reduction with Weighted Reconstruction and Correlation Losses for Efficient Text Embedding","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Embedding; Computer science; Language model; Benchmark (surveying); Similarity (geometry); Latency (audio); Reduction (mathematics); Dimension (graph theory); Correlation; Dimensionality reduction; Code (set theory); Source lines of code; Artificial intelligence; Machine learning; Pattern recognition (psychology); Data mining; Mathematics; Programming language","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":[0.0002048759,0.00009011645,0.0000900054,0.0001623501,0.0001935475,0.0000902867,0.00008017643,0.00004943419,0.000004606516],"category_scores_gemma":[0.00001255013,0.00007228529,0.00001841351,0.0003717335,0.00002698835,0.0002913441,0.00005326104,0.00005346487,0.00001447324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003564583,"about_ca_system_score_gemma":0.00002365898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000105264,"about_ca_topic_score_gemma":0.000002322014,"domain_scores_codex":[0.9991449,0.00002040193,0.0001595649,0.0003660512,0.0001417155,0.0001674044],"domain_scores_gemma":[0.9995313,0.00006622756,0.00007080189,0.000202116,0.00008575778,0.00004384356],"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":[0.00005817058,0.00003318511,0.0006590302,0.00005942388,0.00002717414,0.000002975624,0.001578007,0.178664,0.008392654,0.04338549,0.0006457945,0.7664942],"study_design_scores_gemma":[0.0003073781,0.00006540381,0.0003386708,0.00004271531,0.000006232479,0.00007350093,0.0001938369,0.9951729,0.002008969,0.001565023,0.0001183369,0.0001070576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4059884,0.00001581008,0.5926857,0.0002492474,0.0003817538,0.0001837044,3.128901e-7,0.0002379353,0.0002571082],"genre_scores_gemma":[0.863623,0.000008877721,0.1357552,0.00002156598,0.00006641032,0.00002036836,0.00000518409,0.000008213125,0.00049118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8165089,"threshold_uncertainty_score":0.2947708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0163221336043099,"score_gpt":0.2510149713938844,"score_spread":0.2346928377895745,"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."}}