{"id":"W7131100807","doi":"10.1109/icrai68431.2025.11396704","title":"Optimized Fine-tuning and Pseudo-Data Strategies for Cross-Domain Low-Resource Language Cantonese-English Neural Machine Translation","year":2025,"lang":"","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Machine translation; Pipeline (software); Translation (biology); BLEU; Parallel corpora; Domain (mathematical analysis); Training set","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":[0.004490966,0.001913663,0.0010087,0.001217209,0.001028275,0.00145423,0.002167169,0.001238535,0.00501289],"category_scores_gemma":[0.01989746,0.0007314329,0.0009659275,0.001397601,0.001095044,0.003342335,0.00261499,0.002581851,0.004261536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001294775,"about_ca_system_score_gemma":0.002595677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009208038,"about_ca_topic_score_gemma":0.02080627,"domain_scores_codex":[0.9972799,0.001358389,0.0002025072,0.0006621944,0.000314984,0.0001821073],"domain_scores_gemma":[0.9950577,0.001915789,0.0001725725,0.001523707,0.001199165,0.0001311423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008382893,0.0009802037,0.01002027,0.0008960886,0.0003107419,0.0003861176,0.0007781949,0.3249715,0.03786403,0.01138559,0.02699763,0.5845713],"study_design_scores_gemma":[0.0001938344,0.0002823842,0.002769627,0.00009506271,0.00008732868,0.0002006085,0.0003258647,0.9433069,0.02738745,0.01542105,0.009858707,0.00007130631],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2457648,0.001553897,0.7103151,0.00107953,0.0004456912,0.000860726,0.003452014,0.02453937,0.0119889],"genre_scores_gemma":[0.5962211,0.0002985982,0.3837293,0.0005158735,0.00006180059,0.001598589,0.01114061,0.00238797,0.004046116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009208038,"threshold_uncertainty_score":0.02375078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02057462765299624,"score_gpt":0.3230310482419668,"score_spread":0.3024564205889706,"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."}}