{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002531765,0.0003506662,0.0003045822,0.0003009803,0.0003279844,0.0002240899,0.001735984,0.0002422774,0.00004526632],"category_scores_gemma":[0.00002084987,0.0004156718,0.0002044046,0.0002601643,0.0001626953,0.0006365057,0.002684633,0.0004902735,0.00004053416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003837832,"about_ca_system_score_gemma":0.0004106117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007977206,"about_ca_topic_score_gemma":0.00001488668,"domain_scores_codex":[0.9977532,0.0001495311,0.00024586,0.001310966,0.0001364132,0.0004040252],"domain_scores_gemma":[0.9983133,0.00006858738,0.000284408,0.000884336,0.000273889,0.0001754827],"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":[0.00001141906,0.00002996949,0.001059918,0.00002262914,0.00003920577,0.00004927603,0.0008537758,0.92269,0.0001892713,0.07475481,0.00001784415,0.0002819035],"study_design_scores_gemma":[0.0002988071,0.00001877326,0.00009075837,0.00007675943,0.00003895206,0.000009647654,0.00004094324,0.9396465,0.0002201091,0.05914406,0.00001842691,0.0003962614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4251367,0.00008014197,0.5735327,0.00001866569,0.0005978741,0.0001052398,0.000006092944,0.0001114192,0.0004111558],"genre_scores_gemma":[0.9285369,0.00001888022,0.07000852,0.00007490201,0.0003993835,5.78068e-7,0.000005023191,0.00001900417,0.000936829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5035242,"threshold_uncertainty_score":0.9998295,"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."}}