{"id":"W3213418658","doi":"10.18653/v1/2021.mrl-1.11","title":"Small Data? No Problem! Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Language model; Second-generation programming language; Code (set theory); Resource (disambiguation); Variety (cybernetics); Training set; Programming language; Set (abstract data type); Fifth-generation programming language; Programming paradigm","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006235113,0.001919386,0.001335928,0.001002696,0.001261865,0.003362424,0.00352175,0.001723931,0.007594994],"category_scores_gemma":[0.02389784,0.001137478,0.001899312,0.001486952,0.001898483,0.01473709,0.004477005,0.006245129,0.006235125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001119593,"about_ca_system_score_gemma":0.001607109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01124413,"about_ca_topic_score_gemma":0.01790703,"domain_scores_codex":[0.9973443,0.001301412,0.0001475855,0.0007079163,0.0003275346,0.0001713398],"domain_scores_gemma":[0.9907354,0.005209757,0.0001995839,0.002527617,0.0008457814,0.0004818761],"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":[0.002132428,0.0006663582,0.02450403,0.001575091,0.001254656,0.0009762652,0.002101202,0.1789928,0.01567857,0.05008725,0.241077,0.4809544],"study_design_scores_gemma":[0.0004127255,0.0003914182,0.00356185,0.0004198712,0.0002730218,0.0004698255,0.001650646,0.7446854,0.01371869,0.1492141,0.08505466,0.0001477302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1899845,0.007761369,0.6902302,0.0401938,0.002775076,0.0004777896,0.01557721,0.02881962,0.02418048],"genre_scores_gemma":[0.5542475,0.002809872,0.38023,0.006059372,0.0008673729,0.0008676629,0.0383595,0.005226807,0.01133194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01124413,"threshold_uncertainty_score":0.03297478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1216007999799113,"score_gpt":0.2963027386983271,"score_spread":0.1747019387184158,"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."}}