{"id":"W2168838823","doi":"10.5555/1931390.1931428","title":"Using Markov chains to exploit word relationships in information retrieval","year":2007,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Exploit; Query expansion; Computer science; Markov chain; Process (computing); Information retrieval; Term (time); Word (group theory); Markov process; Natural language processing; Mathematics; Machine learning; Statistics; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001365499,0.0005484591,0.0006441161,0.00160548,0.0004440937,0.0007504523,0.0006191267,0.000707667,0.001463411],"category_scores_gemma":[0.006175009,0.0004984577,0.0005901119,0.002026863,0.0007353983,0.003189198,0.0009088329,0.001055181,0.0005186487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006326426,"about_ca_system_score_gemma":0.0008841951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004444947,"about_ca_topic_score_gemma":0.004785601,"domain_scores_codex":[0.9990175,0.0004578952,0.00006047154,0.000154284,0.0002357636,0.00007407976],"domain_scores_gemma":[0.9956671,0.003575761,0.0002239349,0.0002835199,0.0001932431,0.00005639005],"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":[0.000512866,0.0002597217,0.003025038,0.0002671537,0.0001456202,0.0003335559,0.0004829419,0.3726583,0.01875703,0.05821844,0.004614023,0.5407252],"study_design_scores_gemma":[0.00004423687,0.00006679803,0.0004151868,0.00002156768,0.00003068125,0.0001183699,0.00002382782,0.9579654,0.003616439,0.03560898,0.002059089,0.00002942455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03698978,0.001377057,0.9588099,0.0003409842,0.00004185359,0.0001042799,0.0001032602,0.0008096568,0.001423325],"genre_scores_gemma":[0.5274222,0.002799667,0.4635628,0.0003468473,0.0002167413,0.0003692919,0.000768599,0.000172675,0.004341264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004444947,"threshold_uncertainty_score":0.008838177,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06257794759449921,"score_gpt":0.2945246859432514,"score_spread":0.2319467383487522,"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."}}