{"id":"W2067372181","doi":"10.1145/1236181.1236182","title":"Introduction to special issue on reasoning in natural language information processing","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Artificial intelligence; Natural language processing; Question answering; Perspective (graphical); Heuristic; Natural language; Reasoning system; Analytic reasoning; Opportunistic reasoning; Model-based reasoning; Natural language understanding; Natural (archaeology); Knowledge representation and reasoning","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005022583,0.0003916114,0.0002913578,0.001619813,0.0004686042,0.001354966,0.001008382,0.0002017012,0.00009113858],"category_scores_gemma":[0.0002777856,0.0003786315,0.00008295239,0.002170739,0.00004543888,0.01233741,0.00004233009,0.0007964059,0.0003064132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004744255,"about_ca_system_score_gemma":0.0001617134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001455221,"about_ca_topic_score_gemma":0.00010304,"domain_scores_codex":[0.9973599,0.00006902211,0.0008709073,0.0003892722,0.0007553814,0.0005554875],"domain_scores_gemma":[0.998489,0.00003876141,0.0004162924,0.000698194,0.0002473815,0.0001103768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006886438,0.00006019523,0.00000600417,0.0001364317,0.000003633473,0.000008790757,0.01904001,0.001307479,0.0002996872,0.000464489,0.001089322,0.9775151],"study_design_scores_gemma":[0.01044026,0.001932004,0.004867257,0.007487044,0.0001708859,0.00119476,0.07610893,0.3036185,0.3763128,0.007958246,0.2005707,0.009338639],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005351335,0.0003737488,0.9747399,0.008305392,0.0008217883,0.0008372576,0.00001765469,0.00168977,0.007863156],"genre_scores_gemma":[0.7323985,0.000002491514,0.263295,0.001920546,0.001822534,0.0001012032,0.0001191752,0.00002437354,0.0003161988],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9681765,"threshold_uncertainty_score":0.9998665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003288075048748674,"score_gpt":0.2430932816653218,"score_spread":0.2398052066165732,"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."}}