{"id":"W4226059645","doi":"10.1162/tacl_a_00471","title":"TopiOCQA: Open-domain Conversational Question Answering with Topic Switching","year":2022,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"Minnow Environmental (Canada); Research Canada; Microsoft (Canada); McGill University","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Conversation; Computer science; Question answering; Open domain; Domain (mathematical analysis); Information retrieval; Interdependence; Natural language processing; Artificial intelligence; Relevance (law); Code (set theory); Linguistics; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006251952,0.00008483184,0.0001272042,0.00007006726,0.0008073392,0.00008607232,0.0007350856,0.00002849396,0.00001199987],"category_scores_gemma":[0.0001970824,0.00008025282,0.00007655113,0.0002680215,0.00001141874,0.0001107693,0.00008183779,0.000168213,6.321401e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004196202,"about_ca_system_score_gemma":0.0002498195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007153599,"about_ca_topic_score_gemma":0.00001775618,"domain_scores_codex":[0.9987488,0.000102055,0.0002918787,0.0002071946,0.0005162236,0.0001337964],"domain_scores_gemma":[0.9985244,0.0004337468,0.0003316965,0.0002057785,0.0004780396,0.00002635288],"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":[0.00001103007,0.00004875907,0.001245457,0.000009972111,0.00004227079,1.610443e-7,0.0004062768,0.6655409,0.00001693351,0.3321195,0.00004215315,0.0005165403],"study_design_scores_gemma":[0.001399614,0.0001450334,0.004094598,0.00002409444,0.00005032672,0.000006773493,0.0001851201,0.8025433,0.0001291532,0.1759381,0.01526765,0.0002162224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004479512,0.000009144667,0.9917049,0.001450854,0.001070447,0.0003763602,0.00004969589,0.00004505117,0.0008140377],"genre_scores_gemma":[0.8094958,3.717986e-7,0.1897228,0.0001406722,0.00007873505,0.00005678426,0.00001577289,0.00000723056,0.0004818451],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8050163,"threshold_uncertainty_score":0.6209481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01518758435261074,"score_gpt":0.2579240160992712,"score_spread":0.2427364317466605,"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."}}