{"id":"W3021780374","doi":"10.48550/arxiv.2004.14560","title":"RikiNet: Reading Wikipedia Pages for Natural Question Answering","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Paragraph; Question answering; Computer science; Open domain; Reading (process); Dual (grammatical number); Natural (archaeology); Natural language processing; Information retrieval; Set (abstract data type); Artificial intelligence; Natural language; Domain (mathematical analysis); Questions and answers; World Wide Web; Linguistics; Programming language; Mathematics","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":[0.000205478,0.0002690762,0.0002851991,0.0001608931,0.0001314835,0.0001533518,0.001365683,0.0002049184,0.000002749851],"category_scores_gemma":[0.00008676838,0.0003284267,0.00018142,0.0002643351,0.00003335782,0.0004389925,0.001330417,0.0005157525,0.0000144066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001867483,"about_ca_system_score_gemma":0.0001031889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006795506,"about_ca_topic_score_gemma":0.00002195795,"domain_scores_codex":[0.99819,0.00006442016,0.0001881073,0.001151742,0.00008137408,0.0003243934],"domain_scores_gemma":[0.9986877,0.000113274,0.0001920573,0.0007541696,0.0001196313,0.0001331996],"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":[0.00005457728,0.00003855997,0.001675826,0.0004369175,0.0001288404,0.000284418,0.0010216,0.3234726,0.0009867058,0.6611406,0.0006786217,0.01008075],"study_design_scores_gemma":[0.0002560228,0.00002567046,0.0004372133,0.000116497,0.00003739934,0.000002752729,0.00003054239,0.9534475,0.0002637863,0.04423375,0.0007868387,0.0003620492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06323363,0.0000954253,0.9333925,0.0004750482,0.001402461,0.0003300134,0.000006872636,0.0004452898,0.0006187576],"genre_scores_gemma":[0.9697507,0.00009490913,0.02916474,0.0001277717,0.000330041,0.000001845695,0.00001862312,0.00001929642,0.0004920948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.906517,"threshold_uncertainty_score":0.9999168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08778468336748627,"score_gpt":0.2043180002290689,"score_spread":0.1165333168615826,"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."}}