{"id":"W1977563360","doi":"10.1145/1088463.1088490","title":"Augmenting conversational dialogue by means of latent semantic googling","year":2005,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Conversation; Semantics (computer science); Search engine indexing; Closeness; Information retrieval; World Wide Web; Probabilistic latent semantic analysis; Natural language processing; Latent semantic analysis; Semantic computing; Artificial intelligence; Semantic Web; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002178324,0.001231456,0.0009120661,0.001990382,0.0009716506,0.002191492,0.001079012,0.0006842816,0.004495756],"category_scores_gemma":[0.009631496,0.0004311662,0.001147808,0.00123705,0.001072748,0.006274785,0.003030658,0.001266154,0.002057391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007050272,"about_ca_system_score_gemma":0.001019507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00404414,"about_ca_topic_score_gemma":0.004536101,"domain_scores_codex":[0.9974622,0.001209594,0.00009752882,0.0006055278,0.0004733581,0.0001518537],"domain_scores_gemma":[0.9963295,0.002416725,0.0002558823,0.0005348496,0.0003483717,0.0001147371],"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":[0.001673532,0.0005282772,0.005006765,0.001020838,0.000164572,0.0003203854,0.006545212,0.02521456,0.05165293,0.04402085,0.005722684,0.8581294],"study_design_scores_gemma":[0.0001617184,0.0004568809,0.004290385,0.0001537083,0.0002123718,0.0003780359,0.002185834,0.7902678,0.03263786,0.1257508,0.04328178,0.0002228075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04103481,0.0004339154,0.9436247,0.000403201,0.0000972475,0.0002482326,0.0006975101,0.007943471,0.005516978],"genre_scores_gemma":[0.4409557,0.0003986879,0.5507807,0.0002481305,0.0001409518,0.0004268584,0.002366066,0.000614893,0.004068022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004495756,"threshold_uncertainty_score":0.01503986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01205768151490043,"score_gpt":0.2492630428507604,"score_spread":0.23720536133586,"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."}}