{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003226479,0.0003598366,0.0003667086,0.0002482831,0.0002382006,0.0002146194,0.002000035,0.0002218994,0.00002468225],"category_scores_gemma":[0.00003021626,0.0003787208,0.0001383217,0.0004379329,0.00009345905,0.0004836873,0.002300401,0.0005206733,0.00006091673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002340066,"about_ca_system_score_gemma":0.0002620904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002645388,"about_ca_topic_score_gemma":0.00008609668,"domain_scores_codex":[0.9974858,0.0001128496,0.0002370952,0.001501952,0.0001502639,0.0005120479],"domain_scores_gemma":[0.9976409,0.00006531696,0.0002914947,0.001575448,0.0002421909,0.0001846245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004816823,0.00005731096,0.003018594,0.0001881314,0.0001834706,0.0008748262,0.001239169,0.8801054,0.001047834,0.1126427,0.00006398037,0.0005303342],"study_design_scores_gemma":[0.0003863299,0.00003479484,0.00007834938,0.0003456848,0.00004647762,0.00001807726,0.0000648092,0.9826897,0.002197945,0.0135127,0.0001059461,0.000519147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3948947,0.00002881156,0.6036107,0.00003837952,0.0004211766,0.0001312444,0.000001388422,0.0002526409,0.0006209688],"genre_scores_gemma":[0.8821416,0.0000467645,0.1166473,0.0001293269,0.0002185067,8.425313e-7,0.000003696091,0.00002227787,0.0007896697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4872469,"threshold_uncertainty_score":0.9998665,"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."}}