{"id":"W2950912838","doi":"","title":"Enhancing Sentence Embedding with Generalized Pooling","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Pooling; Embedding; Sentence; Computer science; Artificial intelligence; Natural language processing; Inference; Representation (politics); Redundancy (engineering); Theoretical computer science; Machine learning","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":[0.0009553122,0.001206476,0.0007289658,0.0007277827,0.0002237931,0.0006745411,0.0007708733,0.0006218117,0.002433643],"category_scores_gemma":[0.002812209,0.0002375682,0.0008546127,0.0008430282,0.0003492123,0.002344663,0.001315656,0.0008689757,0.001023721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00037013,"about_ca_system_score_gemma":0.0004162206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001718314,"about_ca_topic_score_gemma":0.002869869,"domain_scores_codex":[0.99955,0.0001564426,0.00002609178,0.0001274558,0.00008978622,0.00005009791],"domain_scores_gemma":[0.9993289,0.0002739857,0.00006540133,0.0001460743,0.0001533753,0.00003240749],"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":[0.0002738319,0.0002046531,0.001650978,0.0004058919,0.0002137704,0.0002134507,0.0004835843,0.08238633,0.08395319,0.01681444,0.01671325,0.7966866],"study_design_scores_gemma":[0.00002093297,0.0002034962,0.001703776,0.00002519593,0.0001186663,0.0001301129,0.00006534679,0.9427672,0.02489535,0.02342553,0.006608425,0.0000358953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04015446,0.001131568,0.9533756,0.0003455817,0.0001536197,0.00005967083,0.0002803511,0.002213203,0.002285853],"genre_scores_gemma":[0.7145345,0.001197818,0.2720635,0.0005417511,0.0004079952,0.0001832205,0.001421147,0.0005151808,0.009134848],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002433643,"threshold_uncertainty_score":0.008141398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06293993825929173,"score_gpt":0.2007202407233379,"score_spread":0.1377803024640462,"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."}}