{"id":"W3119707607","doi":"","title":"Joint Training for Learning Cross-lingual Embeddings with Sub-word Information without Parallel Corpora","year":2020,"lang":"en","type":"article","venue":"Joint Conference on Lexical and Computational Semantics","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Natural language processing; Word (group theory); Lexicon; Artificial intelligence; Benchmark (surveying); Similarity (geometry); Resource (disambiguation); Joint (building); Linguistics","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":[0.000200715,0.0001956757,0.0002878117,0.00006425963,0.0002567971,0.0005405521,0.0001895618,0.00007726954,0.000006323906],"category_scores_gemma":[0.0001312629,0.0001644958,0.00005868902,0.0001334291,0.00008981009,0.0005751754,0.0001050911,0.0003021618,0.00001378482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001975142,"about_ca_system_score_gemma":0.0001824278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004125893,"about_ca_topic_score_gemma":0.000001021893,"domain_scores_codex":[0.9985096,0.00003161312,0.0004263583,0.0003524893,0.0004140303,0.0002658699],"domain_scores_gemma":[0.9990473,0.0001064801,0.0002358768,0.00009901064,0.000315517,0.0001957666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001364938,0.00003668384,0.0009392375,0.0001145768,0.00003419745,0.00000773389,0.005473648,0.3422277,0.0001323462,0.5748029,0.00003427818,0.07606018],"study_design_scores_gemma":[0.0008531105,0.0004377642,0.003417186,0.00009140818,0.000007587681,0.00001869452,0.0002062379,0.966337,0.0001047589,0.02802489,0.0002604996,0.0002408753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2226755,0.000005254811,0.7715459,0.00517044,0.00005484418,0.0001999589,0.000003831233,0.0001275396,0.0002167074],"genre_scores_gemma":[0.8305511,0.000004219408,0.1677755,0.001514285,0.00009424,0.00001342973,0.00002346676,0.000007474488,0.00001621406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6241093,"threshold_uncertainty_score":0.6707945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09927202779614587,"score_gpt":0.2928176832555031,"score_spread":0.1935456554593573,"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."}}