{"id":"W2951626663","doi":"10.48550/arxiv.1809.05524","title":"Extending Neural Generative Conversational Model using External Knowledge Sources","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Perplexity; Computer science; Utterance; Generative grammar; Coherence (philosophical gambling strategy); Natural language processing; Connectionism; Knowledge base; Generative model; Artificial intelligence; Sequence (biology); Focus (optics); Artificial neural network; Language model","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":[0.001278881,0.0009150089,0.0006399997,0.0006912032,0.0005788794,0.001036266,0.00139547,0.001065546,0.003142976],"category_scores_gemma":[0.004198562,0.000573959,0.000871095,0.0005321905,0.0005222626,0.001831116,0.001366823,0.00183208,0.001277197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007791633,"about_ca_system_score_gemma":0.0009330515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00962614,"about_ca_topic_score_gemma":0.01409171,"domain_scores_codex":[0.999454,0.0002433318,0.00002109206,0.0001741056,0.00006318728,0.00004440966],"domain_scores_gemma":[0.9982601,0.001227716,0.00005726279,0.000162932,0.0002212233,0.00007084793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002647743,0.0002434758,0.003002421,0.0001632357,0.0002034928,0.0003723762,0.001102064,0.8047947,0.006804434,0.0149435,0.005436546,0.1626691],"study_design_scores_gemma":[0.000004831616,0.000008895198,0.00008466907,0.000004047274,0.000009160983,0.00001274014,0.00001149622,0.9959687,0.0003702588,0.003074537,0.0004466787,0.00000395226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1049104,0.0008379967,0.8811733,0.0009938255,0.0001855348,0.0001241887,0.0005438764,0.003180319,0.008050446],"genre_scores_gemma":[0.8788534,0.0003476267,0.1097696,0.0003624428,0.0001364082,0.0002222218,0.00145941,0.0003137513,0.008535093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00962614,"threshold_uncertainty_score":0.01914024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1666798095510348,"score_gpt":0.2341611033931835,"score_spread":0.06748129384214871,"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."}}