{"id":"W4408834179","doi":"10.1051/itmconf/20257605013","title":"Natural Language Processing Techniques for Information Retrieval Enhancing Search Engines with Semantic Understanding","year":2025,"lang":"en","type":"article","venue":"ITM Web of Conferences","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Information retrieval; Search engine; Semantic search; Natural language processing; Human–computer information retrieval; Artificial intelligence","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":[0.0003285327,0.00008365866,0.0001392834,0.0002348868,0.00008859806,0.000190319,0.0003422493,0.00004074971,0.000001353624],"category_scores_gemma":[0.00005683028,0.00006478663,0.00002310297,0.0003185928,0.00004050677,0.0007986282,0.00006417271,0.00009074056,2.754849e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003929148,"about_ca_system_score_gemma":0.0007885728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003487406,"about_ca_topic_score_gemma":0.00004585653,"domain_scores_codex":[0.9992728,0.00001645459,0.0002125748,0.0001323964,0.0002074651,0.0001583326],"domain_scores_gemma":[0.9994501,0.0001154854,0.00008324633,0.0001451973,0.0001886256,0.00001738673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001336751,0.00003451322,0.002001835,0.0022959,0.00007797164,0.000002728879,0.01328077,0.0003352799,0.03305654,0.6320359,0.0000587036,0.3166862],"study_design_scores_gemma":[0.0003289442,0.00009923059,0.0001337196,0.0009456498,0.0000136273,0.000003257113,0.004368306,0.7754914,0.2155681,0.00262898,0.0002436261,0.000175192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03775164,0.000208881,0.9578623,0.0003836445,0.00008844712,0.0002302817,8.943463e-7,0.0001305836,0.003343331],"genre_scores_gemma":[0.9606358,0.000005336101,0.03922791,0.00004556378,0.00001903739,0.000006498391,0.000002208842,0.000002004588,0.00005562945],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9228842,"threshold_uncertainty_score":0.2641922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02692447611721513,"score_gpt":0.2920163499823629,"score_spread":0.2650918738651478,"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."}}