{"id":"W4404783575","doi":"10.18653/v1/2024.emnlp-main.176","title":"Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ubisoft (Canada)","funders":"","keywords":"Computer science; Zero (linguistics); Artificial intelligence; Transfer (computing); Shot (pellet); Natural language processing; Materials science; 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":[0.006643828,0.001384779,0.0008414244,0.001512802,0.0008156679,0.001044734,0.002488626,0.001836641,0.002520173],"category_scores_gemma":[0.02671554,0.0005491577,0.0008135259,0.00108096,0.001422054,0.00204637,0.003721606,0.00209462,0.001695894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008319126,"about_ca_system_score_gemma":0.001318551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003504538,"about_ca_topic_score_gemma":0.007051395,"domain_scores_codex":[0.9944951,0.002904329,0.000255893,0.001315023,0.0008095591,0.0002200743],"domain_scores_gemma":[0.9799789,0.0120669,0.0007039158,0.004412235,0.002531019,0.0003069821],"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":[0.0009682375,0.001178525,0.0211247,0.001038628,0.0004252604,0.001246902,0.002158422,0.3592156,0.05024404,0.008303689,0.02526833,0.5288277],"study_design_scores_gemma":[0.0001019273,0.0004508705,0.004866909,0.00007193877,0.00005786615,0.0006919815,0.0005556954,0.9130561,0.06034499,0.01034083,0.009342464,0.0001184152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3576916,0.0007301037,0.6088636,0.0005674033,0.0004530235,0.0005254022,0.002710553,0.02296728,0.005491136],"genre_scores_gemma":[0.7312777,0.0001421543,0.2534032,0.0004598155,0.00005591056,0.0006024301,0.008948738,0.00166789,0.003442147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006643828,"threshold_uncertainty_score":0.03513634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08761482541301252,"score_gpt":0.3773652785887547,"score_spread":0.2897504531757422,"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."}}