{"id":"W2119388680","doi":"10.3115/1220175.1220240","title":"Improved discriminative bilingual word alignment","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Discriminative model; Generative grammar; Computer science; Word (group theory); Word error rate; Artificial intelligence; Machine translation; Natural language processing; Bilingual dictionary; Generative model; Selection (genetic algorithm); Translation (biology); Training set; Statistical model; Machine learning; Speech recognition; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001315521,0.0001084599,0.00009011827,0.00006689437,0.00006415094,0.0001428126,0.0006176306,0.00004056846,0.00001531692],"category_scores_gemma":[0.00002267891,0.00007788438,0.00003688993,0.0002151631,0.00003436006,0.0003367369,0.0002539474,0.0000853027,0.00000925575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000539602,"about_ca_system_score_gemma":0.00004510075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002782503,"about_ca_topic_score_gemma":0.00004070341,"domain_scores_codex":[0.9991642,0.00002157095,0.0001447642,0.0002926329,0.0001679217,0.0002089326],"domain_scores_gemma":[0.9995064,0.00003218375,0.00005302943,0.0003164781,0.00005959059,0.00003230472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003671387,0.0001068065,0.00006189993,0.00001220708,0.000005969284,0.00002504313,0.0004305745,0.000001491273,0.03584121,0.7261829,0.002877454,0.2344508],"study_design_scores_gemma":[0.0002127812,0.00008363228,0.0001640895,0.0000207239,0.000005065402,0.00001456608,0.00005157202,0.01729875,0.7045533,0.2758031,0.001448947,0.0003435235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003763629,0.0003443189,0.9874011,0.0009256429,0.0001115871,0.000127991,6.828287e-7,0.0009764376,0.006348665],"genre_scores_gemma":[0.5084329,7.168363e-7,0.4893753,0.0001747891,0.00004089333,0.000006820893,0.000001329418,0.000004013198,0.001963311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6687121,"threshold_uncertainty_score":0.3176033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00950746876754677,"score_gpt":0.2645663555949464,"score_spread":0.2550588868273996,"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."}}