{"id":"W1989867740","doi":"10.3115/1118693.1118705","title":"Extensions to HMM-based statistical word alignment models","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Bigram; Hidden Markov model; Computer science; Word (group theory); Viterbi algorithm; Speech recognition; Artificial intelligence; Machine translation; Natural language processing; Translation (biology); Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001043314,0.0001067836,0.0001053485,0.00006677774,0.00007588646,0.0001244084,0.0005946169,0.00004014104,0.0001712126],"category_scores_gemma":[0.00005092648,0.00008320098,0.00002466871,0.0002747394,0.00002025478,0.000227332,0.000196441,0.00008883855,0.0001444477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004591379,"about_ca_system_score_gemma":0.00001536439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002564799,"about_ca_topic_score_gemma":0.000004645152,"domain_scores_codex":[0.9989444,0.00002820979,0.0001450343,0.00033207,0.0002974935,0.0002528005],"domain_scores_gemma":[0.999182,0.00008801908,0.00002131918,0.0004769962,0.00006563985,0.0001659787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000286252,0.0001216037,0.000004045049,0.000007558469,0.00000399147,0.00007428615,0.0002303726,0.0004870882,0.001293106,0.7043689,0.06838417,0.225022],"study_design_scores_gemma":[0.00009602594,0.00006286358,0.000008411412,0.00002268025,0.000002640646,0.0000065891,0.000004008165,0.8887045,0.007612553,0.1015112,0.001778767,0.0001897468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001107758,0.0001656394,0.9910833,0.004551579,0.00006103797,0.0001357412,0.000002702505,0.0008156311,0.003073579],"genre_scores_gemma":[0.3002116,0.00000176934,0.6954706,0.003690775,0.00001171221,0.00001611202,7.317532e-7,0.000005348577,0.0005913695],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8882174,"threshold_uncertainty_score":0.3392837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03464454925532364,"score_gpt":0.2797569324102551,"score_spread":0.2451123831549314,"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."}}