{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0122037,0.002140032,0.001487624,0.003390763,0.00099368,0.003398265,0.001987271,0.002124491,0.003604553],"category_scores_gemma":[0.03435148,0.0005599243,0.00149783,0.00281437,0.0005946276,0.007443707,0.004014874,0.002938618,0.003304408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016868,"about_ca_system_score_gemma":0.001802912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009764874,"about_ca_topic_score_gemma":0.0131167,"domain_scores_codex":[0.9900303,0.006751821,0.0006454022,0.001359582,0.0008760985,0.0003367616],"domain_scores_gemma":[0.9766827,0.01764223,0.0004062811,0.002190877,0.002520456,0.0005574576],"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":[0.003117843,0.002157377,0.03240322,0.001380242,0.0039509,0.0004019745,0.001124739,0.1246419,0.007364401,0.006609255,0.0516713,0.7651769],"study_design_scores_gemma":[0.0002509017,0.0007965275,0.005848217,0.0001907071,0.0009837814,0.0002710027,0.001118214,0.9616428,0.007858173,0.01339205,0.007548671,0.0000989734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5994585,0.01572407,0.3341468,0.002659475,0.002871639,0.0007382498,0.01256885,0.01379878,0.01803357],"genre_scores_gemma":[0.8777215,0.001784895,0.08768651,0.0004930767,0.0004199732,0.0004094363,0.02559002,0.0009744075,0.004920041],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0122037,"threshold_uncertainty_score":0.06454009,"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."}}