{"id":"W3201505982","doi":"10.1007/978-981-16-2380-6_51","title":"On Profiling Space Reduction Efficiency in Vector Space Modeling-Based Natural Language Processing","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières; Université du Québec à Montréal","funders":"","keywords":"Automatic summarization; Computer science; Space (punctuation); Reduction (mathematics); Salient; Profiling (computer programming); Artificial intelligence; Natural language processing; Data mining; Algorithm; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005121955,0.0005195077,0.0006424715,0.0004233841,0.0001191773,0.0004941597,0.0004906303,0.0006960692,0.000001680972],"category_scores_gemma":[0.0001398063,0.0004410037,0.00008434513,0.0003728874,0.00005196385,0.0001830331,0.0001381769,0.001683776,6.754815e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002741447,"about_ca_system_score_gemma":0.0001752927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001202682,"about_ca_topic_score_gemma":0.0001006803,"domain_scores_codex":[0.997481,0.00009994503,0.0004952602,0.001017859,0.0004367827,0.0004691105],"domain_scores_gemma":[0.998771,0.0001941776,0.0003039979,0.0005295213,0.0001332187,0.0000681281],"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":[0.00004535705,0.00003379642,0.00001501685,0.0007480154,0.00001169431,0.0003076188,0.0008074621,0.9247082,0.0004617568,0.03841722,0.0000131918,0.0344307],"study_design_scores_gemma":[0.0002213161,0.00006109775,5.150204e-7,0.004932744,0.000008754015,0.00006148071,0.00001065703,0.9912899,0.0003813864,0.002512455,0.00002655744,0.0004930956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006606687,0.1876471,0.8089013,0.0002770039,0.000889802,0.0006137554,0.000001824503,0.0003059634,0.0007026719],"genre_scores_gemma":[0.9761736,0.00007549889,0.02226315,0.00009227479,0.0004912243,0.00003106662,0.00003184433,0.00006148558,0.0007798601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9755129,"threshold_uncertainty_score":0.9998042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01059677281570035,"score_gpt":0.245709131214935,"score_spread":0.2351123583992346,"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."}}