{"id":"W14394360","doi":"","title":"User-relevant access to textual information through flexible identification of terms: a semi-automatic method and software based on a combination of n-grams and surface linguistic filters","year":2000,"lang":"en","type":"article","venue":"RIAO Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Identification (biology); Personalization; Software; Term (time); Task (project management); Domain (mathematical analysis); Human–computer interaction; Artificial intelligence; Natural language processing; Information retrieval; World Wide Web; Programming language; Engineering","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":[0.0004015879,0.00012819,0.0002092971,0.0001198441,0.00005937006,0.0002791112,0.0004820537,0.00006607594,0.00001320792],"category_scores_gemma":[0.0005092503,0.0001154756,0.00001945297,0.0003641024,0.00005540015,0.001047465,0.0001018583,0.0000891763,0.000002632505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002573539,"about_ca_system_score_gemma":0.00007319582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001641213,"about_ca_topic_score_gemma":0.000004403642,"domain_scores_codex":[0.9988639,0.000086609,0.0004134265,0.0002255305,0.0002826827,0.0001278135],"domain_scores_gemma":[0.9988142,0.0002681439,0.0002759008,0.0003403108,0.0002576465,0.00004375045],"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":[0.000101036,0.0002065833,0.001254518,0.00144661,0.000026683,0.000002832358,0.0111113,0.001866652,0.01587925,0.04465619,0.0002290271,0.9232193],"study_design_scores_gemma":[0.0006411547,0.0003691866,0.004752573,0.0009290214,0.00002654529,0.000007063465,0.00004697265,0.7912374,0.1589474,0.04257874,0.0001540492,0.0003099524],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07678213,0.00004872738,0.9222264,0.0002507065,0.00003432623,0.0003544797,0.00001600622,0.0001831687,0.0001040854],"genre_scores_gemma":[0.6876699,0.000008328624,0.3121304,0.0001436007,0.000002663699,0.00001067685,0.00001026222,0.000003474665,0.00002072456],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9229094,"threshold_uncertainty_score":0.4708957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02007228474740815,"score_gpt":0.3164621944393161,"score_spread":0.2963899096919079,"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."}}