{"id":"W4379053645","doi":"10.3390/cmsf2023006003","title":"Developing Conversational Agent Using Deep Learning Techniques","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski","funders":"Centre National pour la Recherche Scientifique et Technique","keywords":"Computer science; Converse; Deep learning; Artificial intelligence; Encoder; Natural language; Recurrent neural network; Architecture; Sequence (biology); Artificial neural network; Natural (archaeology); Natural language processing; Human–computer interaction","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":[0.0002590908,0.00005733761,0.00005772333,0.0001149776,0.0001268401,0.00007710975,0.0002668264,0.00002942748,0.00002095962],"category_scores_gemma":[0.00003390368,0.0000564647,0.00002200347,0.0003282274,0.000009068269,0.0002366991,0.0002502348,0.00007221484,0.00007558762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007782575,"about_ca_system_score_gemma":0.00006765775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002665614,"about_ca_topic_score_gemma":0.000002315738,"domain_scores_codex":[0.9993067,0.00002594673,0.0001228492,0.0002008723,0.0001761717,0.0001674383],"domain_scores_gemma":[0.9997139,0.00004494059,0.00003117582,0.0001365865,0.00004492098,0.00002845584],"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":[9.511064e-7,0.000006750491,0.005067859,0.00002643204,0.0000214354,0.00003607344,0.002096533,0.01818602,0.006261721,0.7039264,0.0001204225,0.2642494],"study_design_scores_gemma":[0.00003727716,0.000004355633,0.0006037065,0.00001247692,8.431114e-7,0.000006357378,0.00007754585,0.9848213,0.006744231,0.004546948,0.00304465,0.0001003366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02594916,0.000008297775,0.9711103,0.0006192613,0.0001384743,0.00005217369,3.298403e-8,0.0009529453,0.001169352],"genre_scores_gemma":[0.3094292,0.000006570669,0.6899642,0.0002480554,0.00004587741,0.000003989037,0.000001236642,0.000004560221,0.0002963038],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9666352,"threshold_uncertainty_score":0.2302564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08726983656625664,"score_gpt":0.3092228061348674,"score_spread":0.2219529695686108,"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."}}