{"id":"W2992721737","doi":"10.48550/arxiv.1912.01706","title":"A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Word (group theory); Computer science; Artificial intelligence; Unsupervised learning; Natural language processing; Mathematics; Geometry","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":[0.004871232,0.0006261977,0.0009146275,0.0004912802,0.000469633,0.0004384216,0.004351503,0.0005560832,0.00005916637],"category_scores_gemma":[0.0006291461,0.000621342,0.0006757474,0.001032763,0.00009393051,0.0005538327,0.004076208,0.001490149,0.00004814313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003103742,"about_ca_system_score_gemma":0.0006374664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003444719,"about_ca_topic_score_gemma":0.00001137187,"domain_scores_codex":[0.9942338,0.0007468463,0.0007289338,0.003164344,0.0003063165,0.0008197292],"domain_scores_gemma":[0.9933158,0.001203312,0.001139956,0.003392784,0.0008077151,0.0001404154],"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":[0.00007659614,0.00006281283,0.001002486,0.0004812868,0.0002364808,0.00003579164,0.002667922,0.9636483,0.0001413702,0.02916813,0.00007505401,0.002403814],"study_design_scores_gemma":[0.0008252642,0.00009285589,0.0001324695,0.0003388029,0.0002011926,0.00002122021,0.0006448363,0.9789338,0.0008135838,0.01398194,0.003354308,0.0006597987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07369289,0.0001382519,0.9200585,0.0002205731,0.0009510537,0.001229385,0.000006561764,0.0004759499,0.00322683],"genre_scores_gemma":[0.451932,0.00004154782,0.5440089,0.000154404,0.000186643,0.000006304548,0.000007540232,0.00005574926,0.003607005],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3782391,"threshold_uncertainty_score":0.9996238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.107240782913354,"score_gpt":0.2717381276094857,"score_spread":0.1644973446961317,"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."}}