{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009237607,0.00006643609,0.00006681436,0.0002918594,0.0001056175,0.0001135282,0.0003221006,0.00005103921,0.00001465117],"category_scores_gemma":[0.0001166148,0.00005980467,0.00001537756,0.0008210701,0.000006246366,0.002228404,0.000258345,0.0001334623,0.00007096407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008196297,"about_ca_system_score_gemma":0.0000310788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007322064,"about_ca_topic_score_gemma":0.00003666755,"domain_scores_codex":[0.9991511,0.00002638774,0.0002633065,0.0001301834,0.0002281828,0.00020086],"domain_scores_gemma":[0.999422,0.00007895233,0.00004683489,0.0003109207,0.00004888873,0.00009239372],"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":[0.0001622679,0.0001398232,0.02217546,0.00002607731,0.000008825073,0.00003548132,0.009778858,0.004124174,0.001480845,0.1708797,0.004774092,0.7864144],"study_design_scores_gemma":[0.0005230783,0.00004554421,0.1272996,0.00007436931,0.00000160382,0.00001251221,0.0005085176,0.8548576,0.001416307,0.001628153,0.01330025,0.000332557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08601868,0.000005528104,0.9098668,0.00022303,0.0001921178,0.0001189618,9.805682e-7,0.00007411119,0.003499832],"genre_scores_gemma":[0.5297555,0.000001674636,0.4696802,0.0003618186,0.00004148083,9.486531e-7,0.000006483403,0.000002681565,0.0001491369],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8507334,"threshold_uncertainty_score":0.2438764,"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."}}