{"id":"W2162017663","doi":"10.3115/1620932.1620940","title":"Multiple word alignment with profile hidden Markov models","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hidden Markov model; Computer science; Word (group theory); Cognate; Task (project management); Set (abstract data type); Artificial intelligence; Maximum-entropy Markov model; Pattern recognition (psychology); Matching (statistics); Markov chain; Sequence labeling; Markov model; Speech recognition; Natural language processing; Variable-order Markov model; Machine learning; Mathematics; Statistics; Linguistics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002795274,0.0009944765,0.001121778,0.001714726,0.0008258976,0.001699682,0.001650982,0.001561822,0.004029671],"category_scores_gemma":[0.01578898,0.001066859,0.001720132,0.002412728,0.0005330289,0.005904312,0.002033175,0.00222877,0.003414528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007538606,"about_ca_system_score_gemma":0.001689608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003187505,"about_ca_topic_score_gemma":0.004854502,"domain_scores_codex":[0.9973869,0.001375553,0.0001769846,0.0005738054,0.0003857804,0.000100893],"domain_scores_gemma":[0.993753,0.004012743,0.0004673345,0.00112078,0.0005200481,0.0001260164],"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":[0.001106626,0.0003384031,0.004250447,0.0007183924,0.0003994344,0.0006356525,0.0007299018,0.2945582,0.01364425,0.06633245,0.01352886,0.6037573],"study_design_scores_gemma":[0.00003102716,0.00005973061,0.0003644297,0.00003460588,0.00003315571,0.0001359227,0.00006023412,0.9188928,0.005015883,0.07089096,0.004448427,0.0000329164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005913012,0.0001777238,0.9889206,0.0001118292,0.0000382299,0.00005703849,0.000439069,0.003580825,0.0007617072],"genre_scores_gemma":[0.1950065,0.0004758696,0.797799,0.0001466369,0.00006744357,0.0002996069,0.003290348,0.0007352916,0.002179284],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004029671,"threshold_uncertainty_score":0.01478302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01168844005839885,"score_gpt":0.2395882213763454,"score_spread":0.2278997813179465,"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."}}