{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001157025,0.0001325715,0.0001139793,0.00006488879,0.00006626402,0.0001535202,0.0007645676,0.00004728671,0.00002195181],"category_scores_gemma":[0.000008979058,0.00008760176,0.00002501992,0.0002550449,0.00001771807,0.0007152885,0.000117919,0.0001014937,0.00001410317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004543627,"about_ca_system_score_gemma":0.00003826598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002688285,"about_ca_topic_score_gemma":0.000007091955,"domain_scores_codex":[0.9989757,0.00001973197,0.00012266,0.0003373088,0.0002923194,0.0002522771],"domain_scores_gemma":[0.9993186,0.00002339594,0.00004998429,0.0004757358,0.0000606356,0.00007164739],"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":[0.00002627201,0.0001136179,0.00008782491,0.00001046342,0.000009787534,0.00005329048,0.0004612023,0.00001761553,0.002707042,0.0748366,0.007077357,0.9145989],"study_design_scores_gemma":[0.000944937,0.0006089141,0.0003449229,0.0001514695,0.0000111736,0.00009450237,0.00005095367,0.4948725,0.2418584,0.2592915,0.0008274529,0.0009432449],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002303755,0.0003845049,0.98283,0.001911803,0.00002907727,0.0002663184,7.808792e-7,0.00134379,0.01092992],"genre_scores_gemma":[0.4432436,0.000002100103,0.5551398,0.0006310847,0.00001405142,0.0000112415,0.000001169665,0.000003735538,0.0009532419],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9136557,"threshold_uncertainty_score":0.3572296,"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."}}