{"id":"W4385572930","doi":"10.18653/v1/2022.emnlp-main.151","title":"Generating Information-Seeking Conversations from Unlabeled Documents","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Benchmark (surveying); Conversation; Context (archaeology); Baseline (sea); Information retrieval; Key (lock); Code (set theory); Resource (disambiguation); Source code; World Wide Web; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003330299,0.002142983,0.00139153,0.002780679,0.001754424,0.00174347,0.002877188,0.002518139,0.004593462],"category_scores_gemma":[0.01927611,0.0006479865,0.001621632,0.002276622,0.0008743668,0.00472185,0.003171261,0.002450445,0.004117652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001781671,"about_ca_system_score_gemma":0.003002253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01347207,"about_ca_topic_score_gemma":0.02289943,"domain_scores_codex":[0.9954644,0.002275004,0.0002401084,0.001346543,0.0004872623,0.0001867726],"domain_scores_gemma":[0.9920225,0.004556956,0.0002879664,0.001584825,0.001144254,0.0004034565],"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":[0.003073651,0.00248436,0.01514822,0.005980289,0.000670523,0.0009668833,0.004381173,0.101247,0.04972302,0.02337436,0.2502214,0.5427292],"study_design_scores_gemma":[0.0004790092,0.0006733065,0.006052429,0.0003226234,0.0002191906,0.0005672359,0.002678969,0.7889485,0.03630481,0.03281185,0.1307478,0.0001944028],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2359461,0.01055962,0.5375025,0.003852469,0.001007266,0.003362328,0.1347943,0.05234643,0.02062896],"genre_scores_gemma":[0.3281482,0.0009056532,0.403775,0.000975445,0.0003186345,0.002403683,0.2558573,0.0009105749,0.006705526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01347207,"threshold_uncertainty_score":0.02678734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01423706942431007,"score_gpt":0.2270842683453938,"score_spread":0.2128471989210837,"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."}}