{"id":"W2997327944","doi":"10.48550/arxiv.1912.12481","title":"Robust Cross-lingual Embeddings from Parallel Sentences","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Sentence; Word (group theory); Embedding; Inference; Speech recognition; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002364862,0.0003883487,0.000429366,0.0001840652,0.0001610203,0.0004270706,0.003363869,0.0004075048,0.00007299284],"category_scores_gemma":[0.00004417667,0.0004457931,0.0002698006,0.0002811591,0.0001154618,0.000594309,0.003608531,0.000766816,0.0003266357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000176812,"about_ca_system_score_gemma":0.0002828425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001312691,"about_ca_topic_score_gemma":0.00006352337,"domain_scores_codex":[0.9971197,0.00009381575,0.0002857083,0.00185119,0.0001739373,0.0004757093],"domain_scores_gemma":[0.9973258,0.0001489135,0.0003290171,0.001832394,0.0001879419,0.0001759446],"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":[0.00001271202,0.00003266412,0.01755218,0.00002881308,0.00006589408,0.0001916008,0.0004734851,0.9556917,0.00001024296,0.02550053,0.0001083926,0.0003317906],"study_design_scores_gemma":[0.0004165388,0.00001813593,0.001737379,0.0001048593,0.00003202111,0.000002564856,0.0001060288,0.9629291,0.00005244648,0.03376469,0.0003275241,0.0005086803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4639173,0.0000635414,0.5329381,0.00005764168,0.001179918,0.0001477072,0.00001374504,0.0002149849,0.00146702],"genre_scores_gemma":[0.9746545,0.00009061542,0.02128233,0.0001526154,0.0002254794,6.095732e-7,0.00002169548,0.00001948641,0.003552678],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5116558,"threshold_uncertainty_score":0.9997994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.120053345690433,"score_gpt":0.2130535212584204,"score_spread":0.09300017556798738,"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."}}