{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001460402,0.0000514044,0.00005340526,0.00006145138,0.0003847895,0.0001886772,0.0004572306,0.00001038461,0.0005213497],"category_scores_gemma":[0.00001736563,0.00005482314,0.00002031914,0.0001726137,0.000004080379,0.001145429,0.0004763898,0.00008929322,0.0000569242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007457706,"about_ca_system_score_gemma":0.00005448261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004868026,"about_ca_topic_score_gemma":0.000008520246,"domain_scores_codex":[0.9992632,0.00003894776,0.0001931505,0.000123612,0.0002620757,0.0001190456],"domain_scores_gemma":[0.9995465,0.00004613954,0.00006464537,0.0002809666,0.00003002765,0.00003176695],"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":[0.000003448519,0.00006191817,0.008846491,0.000008398396,0.00008908506,0.000007928689,0.02206309,0.3492308,0.004569803,0.4432797,0.007264591,0.1645747],"study_design_scores_gemma":[0.0002179471,0.000006845102,0.00009547804,9.686178e-7,0.000001503912,0.00000119679,0.0002627718,0.9879031,0.0001473785,0.001765431,0.00952356,0.00007384147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05859464,0.00001123557,0.9358385,0.0007970059,0.0004487975,0.00007767657,0.000003185926,0.0001526883,0.004076317],"genre_scores_gemma":[0.8010719,6.105693e-7,0.1964926,0.002097043,0.00003257656,0.00002657956,0.0000185966,0.000001962656,0.0002581275],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7424773,"threshold_uncertainty_score":0.5708414,"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."}}