{"id":"W3030512995","doi":"","title":"Evaluating Sub-word Embeddings in Cross-lingual Models.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Word (group theory); Natural language processing; Artificial intelligence; Lexicon; Task (project management); Space (punctuation); Vocabulary; Resource (disambiguation); 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":[0.001466355,0.0001085153,0.000134953,0.00006573172,0.00008554028,0.0002454318,0.0002700293,0.000059636,0.00001997715],"category_scores_gemma":[0.0002680231,0.0001043714,0.00002970305,0.0002506744,0.00001913791,0.0004189084,0.0001783969,0.0001395818,0.000007602949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003843964,"about_ca_system_score_gemma":0.00004019452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001222918,"about_ca_topic_score_gemma":0.00002743525,"domain_scores_codex":[0.9983926,0.0001427835,0.0002626626,0.0004267886,0.0005631353,0.0002120636],"domain_scores_gemma":[0.9994675,0.00007161105,0.00008656937,0.0002115395,0.00007910514,0.00008366117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001868039,0.00001371673,0.001566339,0.00004112711,0.00000683233,0.00001079722,0.09973284,0.2242779,0.004667625,0.0007513145,0.00001157163,0.6689013],"study_design_scores_gemma":[0.000565826,0.00004141646,0.00161074,0.00002897112,0.000007016303,0.000003555546,0.0007098564,0.994669,0.0006486962,0.00156023,0.00003332863,0.0001214224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9574541,0.001661441,0.03932577,0.0005991943,0.00005609523,0.0002141831,7.247127e-7,0.00008434751,0.0006041463],"genre_scores_gemma":[0.9862428,0.00001310763,0.01309859,0.0004293245,0.000170991,0.0000156747,0.000003863263,0.000008594588,0.00001701184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.770391,"threshold_uncertainty_score":0.4256141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08551581455221315,"score_gpt":0.3744345054740225,"score_spread":0.2889186909218093,"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."}}