{"id":"W1551794154","doi":"","title":"Transliteration Generation and Mining with Limited Training Resources","year":2010,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Transliteration; Computer science; Discriminative model; Artificial intelligence; Natural language processing; Joint (building); Training set; Sequence (biology); n-gram; Language model; Machine learning; Engineering","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":[0.00106727,0.001645659,0.001486756,0.001187568,0.0007779317,0.001211017,0.003317048,0.001241609,0.01032858],"category_scores_gemma":[0.00613895,0.0007549986,0.0008591441,0.001628781,0.0005444535,0.003194245,0.00239187,0.001688739,0.01316681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006345846,"about_ca_system_score_gemma":0.001386756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002251279,"about_ca_topic_score_gemma":0.006401252,"domain_scores_codex":[0.9987935,0.0003103469,0.00007709131,0.0004704022,0.0002424774,0.0001061806],"domain_scores_gemma":[0.9963589,0.001301948,0.0002715745,0.001449219,0.0004923426,0.0001260179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005464653,0.0003280363,0.001947515,0.0006615011,0.0001058045,0.0005383462,0.0002246435,0.0409385,0.03976908,0.003916946,0.03733625,0.8736869],"study_design_scores_gemma":[0.0001113145,0.0002317078,0.0007303359,0.00004260181,0.00005428952,0.0006078911,0.0001041786,0.9057549,0.06402391,0.01040385,0.01788556,0.0000494655],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03225607,0.0005582831,0.9114462,0.0004624116,0.0001935927,0.0001986306,0.002230074,0.04882688,0.003827932],"genre_scores_gemma":[0.1887599,0.0003054806,0.7879428,0.0002838925,0.0001262187,0.0003069405,0.01092146,0.00213983,0.009213679],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01032858,"threshold_uncertainty_score":0.03455257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01945453074298198,"score_gpt":0.2420105028488689,"score_spread":0.2225559721058869,"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."}}