{"id":"W2148861208","doi":"10.3115/1626355.1626366","title":"Using word dependent transition models in HMM based word alignment for statistical machine translation","year":2007,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Hidden Markov model; Word (group theory); Word error rate; Machine translation; Phrase; Artificial intelligence; Speech recognition; Natural language processing; Translation (biology); IBM; Transition (genetics); Bayesian probability; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002261536,0.0007409987,0.0008963157,0.0008148995,0.0006149306,0.0009231868,0.001015127,0.001076596,0.002515869],"category_scores_gemma":[0.009800437,0.0007511907,0.0007036777,0.001108522,0.0005060064,0.002302735,0.0008585037,0.0019945,0.002896413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007481163,"about_ca_system_score_gemma":0.001526126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008311309,"about_ca_topic_score_gemma":0.01711971,"domain_scores_codex":[0.9981285,0.0009915823,0.0001044308,0.000345276,0.0003521588,0.00007797852],"domain_scores_gemma":[0.9960135,0.002989988,0.0001944309,0.0002896675,0.0004486891,0.00006361779],"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":[0.0005476289,0.0002387768,0.002848869,0.0003827314,0.0003119466,0.0002011385,0.0004601227,0.3940391,0.02480214,0.01577333,0.004531329,0.5558629],"study_design_scores_gemma":[0.00003068967,0.0000725069,0.0006389659,0.00003019985,0.0000536668,0.00006649541,0.00002792909,0.9775183,0.005978538,0.01173856,0.003792679,0.00005147465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005300031,0.0002975155,0.9922214,0.0001075535,0.00005125933,0.00003395484,0.0001119232,0.001366951,0.0005094376],"genre_scores_gemma":[0.2623644,0.0009504405,0.7298504,0.0002822565,0.0001332169,0.000414885,0.00149337,0.0007334849,0.003777591],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008311309,"threshold_uncertainty_score":0.01652586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0475808348722308,"score_gpt":0.3276871825280877,"score_spread":0.2801063476558568,"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."}}