{"id":"W2250341893","doi":"","title":"Mapping Source to Target Strings without Alignment by Analogical Learning: A Case Study with Transliteration","year":2013,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Transliteration; Computer science; Natural language processing; Phrase; Analogy; Artificial intelligence; Machine translation; Task (project management); Translation (biology); Rule-based machine translation; Machine learning; Linguistics; 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":[0.003982951,0.0008306911,0.0009803104,0.001027784,0.001577722,0.00181968,0.002014724,0.003441906,0.004013176],"category_scores_gemma":[0.02879564,0.0004288512,0.0007947137,0.002504324,0.001608558,0.004666582,0.001912792,0.002096742,0.001483626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007223265,"about_ca_system_score_gemma":0.0005428339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003737371,"about_ca_topic_score_gemma":0.005392193,"domain_scores_codex":[0.995472,0.003084724,0.0003358724,0.0004429277,0.0004989469,0.0001655719],"domain_scores_gemma":[0.9732549,0.02103142,0.0007209156,0.0035806,0.001193732,0.0002184013],"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":[0.002663039,0.005512726,0.03565233,0.003649383,0.000409331,0.03716484,0.03544879,0.09575075,0.03850665,0.03072159,0.015833,0.6986876],"study_design_scores_gemma":[0.00175651,0.004361705,0.02558405,0.0004131159,0.0005218175,0.02971308,0.0238256,0.5814965,0.1568883,0.08422687,0.09088419,0.000328216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9000833,0.0009240702,0.08197398,0.001698929,0.00006223762,0.0003767437,0.0006325123,0.00112852,0.01311973],"genre_scores_gemma":[0.9013769,0.0003512922,0.09303746,0.0002861659,0.00004821015,0.0001655457,0.0005800484,0.0003292841,0.003825058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004013176,"threshold_uncertainty_score":0.0210641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01025360225145763,"score_gpt":0.2590147617676204,"score_spread":0.2487611595161628,"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."}}