{"id":"W2250863190","doi":"10.3115/v1/d14-1051","title":"An I-vector Based Approach to Compact Multi-Granularity Topic Spaces Representation of Textual Documents","year":2014,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Granularity; Computer science; Representation (politics); Information retrieval; Vector space; Natural language processing; Artificial intelligence; Mathematics; Programming language; Pure mathematics","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":[0.001367663,0.0009400513,0.001148271,0.005021498,0.0007045328,0.002407072,0.001589096,0.00114495,0.004096368],"category_scores_gemma":[0.005077295,0.000380369,0.001312402,0.006415865,0.000450696,0.003534524,0.001701671,0.001744996,0.002774541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009083776,"about_ca_system_score_gemma":0.00110009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006766238,"about_ca_topic_score_gemma":0.007231565,"domain_scores_codex":[0.9985498,0.0004400736,0.0001584412,0.0003725917,0.0003227565,0.0001563818],"domain_scores_gemma":[0.99752,0.001096336,0.0001998125,0.0003176206,0.0007176432,0.0001486182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000805216,0.0002860062,0.002077506,0.0005780964,0.0001757938,0.0001347678,0.0008257534,0.02744218,0.01486517,0.0242517,0.02504599,0.9035119],"study_design_scores_gemma":[0.00007986888,0.0002447309,0.002276755,0.0001127056,0.000127274,0.0002293616,0.000573666,0.9193994,0.006499279,0.04552826,0.02484615,0.00008255341],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01355212,0.003754247,0.97493,0.0004769739,0.0002477222,0.0001675824,0.002199738,0.002873644,0.001798062],"genre_scores_gemma":[0.2779436,0.003073081,0.6980144,0.0002548586,0.0006929697,0.0006718584,0.01226649,0.0005499924,0.006532707],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006766238,"threshold_uncertainty_score":0.0137037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06669668175130425,"score_gpt":0.3379462876103425,"score_spread":0.2712496058590382,"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."}}