{"id":"W4200633215","doi":"10.1609/aaai.v36i10.21293","title":"From Good to Best: Two-Stage Training for Cross-Lingual Machine Reading Comprehension","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Set (abstract data type); Natural language processing; Reading (process); Comprehension; Task (project management); Resource (disambiguation); Reading comprehension; Machine learning; Recall; Precision and recall; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0008016448,0.0002511759,0.000334835,0.000160606,0.0006815835,0.0003562323,0.002702014,0.00005020547,0.0000981081],"category_scores_gemma":[0.0003836121,0.0002248926,0.0001499831,0.0005349111,0.0000923082,0.0003170162,0.001268295,0.0004131281,0.00002256064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001042416,"about_ca_system_score_gemma":0.0001242507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000332213,"about_ca_topic_score_gemma":0.00001824695,"domain_scores_codex":[0.9973736,0.00002611458,0.000667286,0.0008059397,0.0006559585,0.0004710815],"domain_scores_gemma":[0.9984336,0.0002339056,0.0003662916,0.0004288744,0.0004057155,0.0001316282],"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":[0.0001719982,0.0001418209,0.0002463503,0.00002815498,0.00002082826,0.000001324026,0.01332497,0.01182659,0.1141779,0.7153935,0.00003556486,0.144631],"study_design_scores_gemma":[0.0000961897,0.000371739,0.00003087855,0.0001281244,0.0000128697,0.000004561493,0.00268142,0.6437089,0.2492109,0.1025137,0.0009104362,0.0003302455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7276096,0.00002412356,0.2646544,0.002630477,0.001193426,0.0008443208,0.00007509203,0.0001454395,0.002823117],"genre_scores_gemma":[0.9682569,0.000002118559,0.03048013,0.0004771589,0.0001726702,0.0001010672,0.000002537547,0.00002148972,0.0004859465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6318823,"threshold_uncertainty_score":0.9170853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.172198085721702,"score_gpt":0.3666931078557866,"score_spread":0.1944950221340846,"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."}}