{"id":"W2916853875","doi":"10.1007/978-3-030-11479-4_5","title":"Deep Learning for Document Representation","year":2019,"lang":"en","type":"book-chapter","venue":"Smart innovation, systems and technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ontario Institute of Technology","funders":"","keywords":"Word2vec; Computer science; Document classification; Representation (politics); Artificial intelligence; Natural language processing; Set (abstract data type); Information retrieval; Categorization; Bag-of-words model","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":[0.0003628865,0.0002084288,0.0003062345,0.0004991676,0.0001520629,0.0002511055,0.000407425,0.0003737462,0.000001672961],"category_scores_gemma":[0.0001279484,0.0001936185,0.00003681381,0.0001729832,0.00004517314,0.0002836791,0.0002941937,0.0002465973,0.0000127554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006341553,"about_ca_system_score_gemma":0.00004599959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002172024,"about_ca_topic_score_gemma":0.000003898512,"domain_scores_codex":[0.9985316,0.000008390759,0.0005276041,0.0005430607,0.0002143887,0.000174889],"domain_scores_gemma":[0.9984135,0.00008803015,0.0004549708,0.0006252468,0.0004101383,0.000008111218],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001133022,0.000001231191,0.0002164093,0.0001243395,0.00002836063,7.645291e-7,0.00005219042,0.0002839197,0.00002346923,0.9363213,0.0003062293,0.06264072],"study_design_scores_gemma":[0.000492308,0.0001856304,0.00007441973,0.0004918037,0.00002290251,0.00003419649,0.0005047898,0.06992126,0.0002123538,0.4049652,0.5224126,0.0006824944],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0002124971,0.00169832,0.9622973,0.0009602536,0.001101024,0.001019279,0.000001691761,0.001201269,0.03150841],"genre_scores_gemma":[0.361672,0.0009014134,0.06254327,0.0001146497,0.0003859164,0.0004942669,0.0001643975,0.0001131131,0.573611],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.899754,"threshold_uncertainty_score":0.7895535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03384537849134838,"score_gpt":0.2627927763798293,"score_spread":0.2289473978884809,"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."}}