{"id":"W3206907172","doi":"10.18653/v1/2022.acl-long.125","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Topic Modeling","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Language model; Fine-tuning; Modular design; Overfitting; Artificial intelligence; Task (project management); Inference; Adapter (computing); Programming language; Computer hardware","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":[0.001961578,0.001951798,0.00129083,0.0006459595,0.0006478883,0.001191256,0.003336716,0.001736049,0.006397656],"category_scores_gemma":[0.008000606,0.0009639036,0.001313354,0.0006471336,0.001125058,0.003107284,0.003131897,0.004032827,0.003293197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001191861,"about_ca_system_score_gemma":0.001499513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008811509,"about_ca_topic_score_gemma":0.01587039,"domain_scores_codex":[0.9988733,0.0002830444,0.0000611115,0.0004353212,0.0001993153,0.0001479226],"domain_scores_gemma":[0.9981269,0.0008586173,0.0000905683,0.0006131359,0.0002212138,0.00008963342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004353038,0.0003956809,0.003086197,0.0002947357,0.0003528002,0.000282644,0.0003611433,0.5270873,0.02169021,0.009308142,0.01426555,0.4224402],"study_design_scores_gemma":[0.00002341947,0.00004646813,0.0002545232,0.00001299302,0.00002329089,0.0000422164,0.00003025622,0.9847264,0.003775317,0.009451046,0.001598157,0.00001603776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05567868,0.0009672241,0.9153187,0.000518082,0.0002052127,0.0001830481,0.0005402852,0.02180029,0.004788307],"genre_scores_gemma":[0.6994587,0.0003706839,0.2856486,0.001098774,0.000130874,0.0005800321,0.002515423,0.002721263,0.007475613],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008811509,"threshold_uncertainty_score":0.0214023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01407345951011647,"score_gpt":0.2517387941339686,"score_spread":0.2376653346238521,"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."}}