{"id":"W1175472468","doi":"10.71781/9898","title":"Extracting and exploiting word relationships for information retrieval","year":2008,"lang":"en","type":"dissertation","venue":"Library and Archives Canada (Government of Canada)","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Information retrieval; Query expansion; Ranking (information retrieval); Independence (probability theory); Ambiguity; Web query classification; Document retrieval; Vector space model; Word (group theory); Representation (politics); Web search query; Search engine; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.00003486815,0.0001797027,0.0002092239,0.00006840475,0.0005420372,0.000109277,0.0002567837,0.00006487226,0.000003070925],"category_scores_gemma":[0.00003886256,0.0001831753,0.00002930571,0.0001293353,0.00002420126,0.002790814,0.00007399236,0.0002807082,3.424807e-9],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009071263,"about_ca_system_score_gemma":0.001674856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003141757,"about_ca_topic_score_gemma":0.002115604,"domain_scores_codex":[0.9977102,0.00004032506,0.0004791046,0.0001675538,0.001355908,0.0002469497],"domain_scores_gemma":[0.9987316,0.0005115404,0.0004186714,0.000155762,0.000003899615,0.0001785255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.002162497,0.00004807775,0.009565791,0.00289614,0.000161652,0.00005115805,0.009895967,0.0001165495,0.005699444,0.59578,0.002150682,0.371472],"study_design_scores_gemma":[0.003558805,0.0005070959,0.3944489,0.001830479,0.0001425603,0.0001278689,0.07224128,0.1023882,0.250562,0.006846362,0.1642369,0.003109527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6357554,0.0007409618,0.01640327,0.003809626,0.001926824,0.002132555,0.0005793537,0.0001278217,0.3385242],"genre_scores_gemma":[0.9760399,0.0003409905,0.01283811,0.000424196,0.00007084425,0.00002410497,0.0002609389,0.00001832301,0.009982569],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5889336,"threshold_uncertainty_score":0.7469671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01116759617123924,"score_gpt":0.1777984621701984,"score_spread":0.1666308659989592,"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."}}