{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002623041,0.0008029427,0.0009168281,0.000775965,0.000545794,0.001147456,0.001807162,0.0007911145,0.007946076],"category_scores_gemma":[0.009596001,0.0008911361,0.001059738,0.001312053,0.0004357799,0.002846971,0.001149165,0.002062459,0.007015465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006830248,"about_ca_system_score_gemma":0.001389245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007005798,"about_ca_topic_score_gemma":0.01381828,"domain_scores_codex":[0.9985529,0.0005142239,0.000137989,0.0003201411,0.0003993834,0.0000753944],"domain_scores_gemma":[0.9957703,0.002423098,0.000185314,0.0008274121,0.0007136031,0.00008028372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006195568,0.0002488788,0.003258343,0.0006961566,0.0004734881,0.0002853992,0.0007682518,0.3900378,0.01737388,0.04488555,0.0144664,0.5268863],"study_design_scores_gemma":[0.00004501801,0.00008151234,0.0007492266,0.00006186584,0.0001045697,0.0001372677,0.00004822051,0.9179367,0.006201328,0.04318341,0.03138851,0.00006232763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005733653,0.0004287214,0.9854033,0.0001543254,0.0001405931,0.00008589938,0.0006593182,0.00527919,0.002115],"genre_scores_gemma":[0.1538064,0.001311973,0.8277475,0.0002768605,0.0002344078,0.0004643627,0.00418101,0.001596242,0.0103814],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007946076,"threshold_uncertainty_score":0.02658224,"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."}}