{"id":"W17684","doi":"10.1111/j.2042-7158.1977.tb11305.x","title":"Word pairs in language modeling for information retrieval","year":2004,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Bigram; Vector space model; Computer science; Word (group theory); Language model; Natural language processing; Artificial intelligence; Constraint (computer-aided design); Term Discrimination; Adjacency list; Information retrieval; Visual Word; Algorithm; Mathematics","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":[0.0002297633,0.00004698589,0.00005609941,0.00009263453,0.00002531218,0.00006731415,0.000242227,0.00003320358,0.000002018567],"category_scores_gemma":[0.00005095969,0.00004336428,0.00002301304,0.0001628142,0.000002670148,0.0009700137,0.00005650555,0.00005029239,0.00001365426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005847706,"about_ca_system_score_gemma":0.0000445864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001194291,"about_ca_topic_score_gemma":0.00003814749,"domain_scores_codex":[0.9994761,0.000004742679,0.000172612,0.00009768351,0.0001072588,0.0001415511],"domain_scores_gemma":[0.9997138,0.00001535323,0.00002105626,0.0001956847,0.00002866912,0.00002540824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001100113,0.00001516777,0.00005255147,0.00002086621,0.000002238262,0.000001686965,0.007076201,0.7609746,0.0001526862,0.17127,0.00001645951,0.06040646],"study_design_scores_gemma":[0.0004392057,0.00001041361,0.00001777844,0.00001083962,4.088445e-7,0.000001217433,0.0002354189,0.9907306,0.0005470192,0.007866246,0.00007849988,0.00006232408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1317142,0.00001347238,0.8662012,0.0005446826,0.0000896841,0.0001250632,2.8933e-7,0.0000972108,0.001214155],"genre_scores_gemma":[0.7681051,9.890597e-7,0.2315487,0.0002917876,0.00001899705,0.000004056816,0.000001501059,0.0000015569,0.00002735288],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6363908,"threshold_uncertainty_score":0.1768344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02039087438294956,"score_gpt":0.2508621982835105,"score_spread":0.2304713239005609,"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."}}