{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001603972,0.002333054,0.001225586,0.002562204,0.0005862078,0.001614513,0.001459352,0.001150495,0.00545776],"category_scores_gemma":[0.00605435,0.0006706914,0.001513429,0.002529594,0.0005685699,0.005074507,0.003590647,0.00196424,0.008707959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00050573,"about_ca_system_score_gemma":0.00121274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002463154,"about_ca_topic_score_gemma":0.004589908,"domain_scores_codex":[0.998399,0.0004512476,0.0001429158,0.0006379142,0.0002273493,0.0001415486],"domain_scores_gemma":[0.9979314,0.0005580076,0.0001780332,0.0006940127,0.0005660673,0.00007256898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004633827,0.000360554,0.002867172,0.0005786677,0.0003503689,0.0003532961,0.000672783,0.02784861,0.03777483,0.009492246,0.02734601,0.8918919],"study_design_scores_gemma":[0.00009843968,0.000486024,0.005515117,0.0001562887,0.0003061208,0.0008711793,0.001156098,0.8389808,0.04743766,0.06100063,0.043817,0.0001746374],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07982123,0.002638482,0.8980313,0.0005007344,0.0006512048,0.0001904001,0.002929203,0.01015825,0.005079226],"genre_scores_gemma":[0.5507572,0.002315735,0.3957094,0.0004941635,0.0006938744,0.000433189,0.02783574,0.002329267,0.01943137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00545776,"threshold_uncertainty_score":0.01825804,"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."}}