{"id":"W7096651338","doi":"","title":"Association for Computational Linguistics. Extensions to HMM-based Statistical Word Alignment Models","year":2013,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Bigram; Word (group theory); Viterbi algorithm; Hidden Markov model; Statistical model; Association (psychology); Error detection and correction","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":[0.005470133,0.002529353,0.002398315,0.005667572,0.001393575,0.005187121,0.00342181,0.004042627,0.2037604],"category_scores_gemma":[0.02627675,0.002620628,0.001849736,0.01141322,0.00211616,0.01168102,0.004817515,0.006397101,0.1710094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001456793,"about_ca_system_score_gemma":0.004615783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006663295,"about_ca_topic_score_gemma":0.005982539,"domain_scores_codex":[0.9952018,0.001410004,0.000787682,0.001335478,0.001106603,0.0001583677],"domain_scores_gemma":[0.9771518,0.01303229,0.001452589,0.00497504,0.002808968,0.0005793397],"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":[0.0001003043,0.00008191646,0.001692449,0.002476977,0.0002217247,0.0003621941,0.0007168219,0.002622016,0.001260818,0.09779133,0.4425952,0.4500783],"study_design_scores_gemma":[0.00007882997,0.00003626516,0.0009639829,0.001363307,0.0000970132,0.000483522,0.0001556435,0.01505933,0.0005842468,0.1421486,0.8389664,0.0000629411],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00148393,0.02962903,0.7360801,0.01898809,0.00848555,0.0006574984,0.0434102,0.04186139,0.1194042],"genre_scores_gemma":[0.04276694,0.03186705,0.6862435,0.006000936,0.004290435,0.004469397,0.06404334,0.01277477,0.1475437],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2037604,"threshold_uncertainty_score":0.6816464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02028263773783219,"score_gpt":0.2955953691796271,"score_spread":0.2753127314417949,"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."}}