{"id":"W3099902934","doi":"","title":"Low-Resource NMT: an Empirical Study on the Effect of Rich Morphological Word Segmentation on Inuktitut","year":2020,"lang":"en","type":"article","venue":"Conference of the Association for Machine Translation in the Americas","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Word (group theory); Linguistics; Philosophy","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001387173,0.0001438569,0.0002423619,0.00005621228,0.0001237036,0.00007010737,0.001268306,0.00006102042,0.000004540345],"category_scores_gemma":[0.0008119831,0.00006950967,0.00009677831,0.0006957198,0.00005875169,0.0001635371,0.0000496338,0.0003045143,0.000001827581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005403443,"about_ca_system_score_gemma":0.00002619068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002131743,"about_ca_topic_score_gemma":0.000007258224,"domain_scores_codex":[0.9975216,0.001197259,0.0003409047,0.0002509714,0.0005542273,0.0001350576],"domain_scores_gemma":[0.9971026,0.001909124,0.0005032173,0.0003737166,0.00008879416,0.00002251335],"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":[0.003197065,0.003353757,0.3130634,0.0002594696,0.0003784902,0.00001018856,0.1788196,0.007898074,0.05773555,0.025949,0.0025355,0.4068],"study_design_scores_gemma":[0.01040956,0.02940969,0.2333898,0.0004108826,0.0004687408,0.000009046851,0.00451983,0.2908384,0.3896329,0.03877573,0.0006424729,0.001492971],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.910219,0.00005835803,0.06090962,0.02630977,0.00006521975,0.001964284,0.00002090116,0.000107639,0.0003452352],"genre_scores_gemma":[0.9966052,0.000001216548,0.002103613,0.001159386,0.00002197805,0.00008533027,0.000008640199,0.000006605537,0.000007987305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.405307,"threshold_uncertainty_score":0.2834522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05020840577988522,"score_gpt":0.3467333131491154,"score_spread":0.2965249073692302,"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."}}