{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001082611,0.001497949,0.0007674993,0.0009094221,0.0003865823,0.0009072061,0.001601523,0.001117647,0.003928488],"category_scores_gemma":[0.005449986,0.0004683904,0.0007972996,0.0008901762,0.0006457068,0.003660476,0.002136976,0.001817095,0.002643421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006864294,"about_ca_system_score_gemma":0.000872405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002464702,"about_ca_topic_score_gemma":0.005492519,"domain_scores_codex":[0.9995449,0.0001418492,0.00003204021,0.0001055484,0.000124421,0.00005115668],"domain_scores_gemma":[0.9988011,0.0005388494,0.00009406143,0.0003354937,0.0001718158,0.00005865502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004148668,0.0003131457,0.001459552,0.0004085194,0.0001640745,0.000384525,0.0002941758,0.4334654,0.02320397,0.02950948,0.02044701,0.4899353],"study_design_scores_gemma":[0.0000184064,0.00005152011,0.00008303502,0.00001072933,0.00001202409,0.00006830991,0.00002502637,0.9833243,0.004603008,0.009373848,0.00241787,0.00001185748],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02217224,0.0003760885,0.9700311,0.0002512017,0.0001119371,0.0001329313,0.0004805806,0.004858344,0.001585506],"genre_scores_gemma":[0.341053,0.0006693483,0.6420302,0.0003161443,0.000163481,0.0008028174,0.004027038,0.001121138,0.009816748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003928488,"threshold_uncertainty_score":0.01314211,"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."}}