{"id":"W2786983967","doi":"10.24963/ijcai.2018/609","title":"An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Conversation; Ranking (information retrieval); Natural language generation; Generative grammar; Margin (machine learning); Utterance; Generator (circuit theory); Artificial intelligence; Process (computing); Information retrieval; Natural language processing; Artificial neural network; Natural language; Machine learning; Programming language","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":[0.0002980282,0.0000723814,0.0001044063,0.00008246833,0.00007933813,0.0001083497,0.0002124435,0.00004896463,0.00001107097],"category_scores_gemma":[0.000006303848,0.00006593331,0.00001667309,0.0001107418,0.0000419848,0.000231786,0.00002235669,0.00002941395,0.00000510977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002061359,"about_ca_system_score_gemma":0.00006614396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001135657,"about_ca_topic_score_gemma":0.00001391087,"domain_scores_codex":[0.9991668,0.00006629127,0.0002066464,0.0002712295,0.0001844925,0.0001045691],"domain_scores_gemma":[0.9991955,0.00003639758,0.00007968201,0.0004385753,0.0001974386,0.00005242818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003349662,0.000263615,0.01038327,0.0002304696,0.00004063197,0.000006962289,0.002836301,0.08880076,0.6676869,0.2118513,0.001258358,0.01660789],"study_design_scores_gemma":[0.0003203637,0.0001807777,0.0003006258,0.000008720713,0.000002454439,5.940111e-7,0.000006215772,0.9078956,0.09109364,0.00007385322,0.00004430593,0.00007289631],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.291256,0.000008825916,0.7080911,0.000111514,0.0002383578,0.00009481869,4.133866e-7,0.00006251561,0.0001364681],"genre_scores_gemma":[0.9040089,1.399367e-7,0.09545964,0.0002553974,0.0002331578,0.00000161785,0.000004490887,0.000004019534,0.00003263625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8190948,"threshold_uncertainty_score":0.2688682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03805082076957427,"score_gpt":0.2712421793445915,"score_spread":0.2331913585750173,"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."}}