{"id":"W3034865274","doi":"10.24963/ijcai.2020/555","title":"Teacher-Student Networks with Multiple Decoders for Solving Math Word Problem","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China; National Research Foundation","keywords":"Computer science; Margin (machine learning); Generalization; Word (group theory); Visualization; Decoding methods; Theoretical computer science; Artificial intelligence; Machine learning; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001396986,0.0001192684,0.0001313441,0.00001754083,0.00009670115,0.0001725706,0.0006161623,0.00003941167,0.000006761551],"category_scores_gemma":[0.0000183995,0.00009045612,0.00004176727,0.0001269111,0.00001090364,0.0002391447,0.0002145162,0.0001088311,0.00000651015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000255716,"about_ca_system_score_gemma":0.0000359661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002565702,"about_ca_topic_score_gemma":0.00008623423,"domain_scores_codex":[0.9989441,0.00001101092,0.0001712091,0.0004081827,0.0001647121,0.0003007683],"domain_scores_gemma":[0.9994365,0.00007953201,0.00005152294,0.000269198,0.00004058352,0.0001226845],"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":[0.0000590397,0.0001645394,0.0359596,0.0001000736,0.0001236328,0.00001927408,0.01209746,0.7208182,0.000219803,0.04804761,0.005633767,0.1767571],"study_design_scores_gemma":[0.0004600368,0.00006746423,0.0002819391,0.00001487948,0.00000457014,0.000001984359,0.0001548194,0.9970211,0.00004319578,0.0001331588,0.00167586,0.0001410056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01150463,0.0000449574,0.9834774,0.00335066,0.00006519138,0.0004161754,1.874394e-7,0.0003096102,0.0008311911],"genre_scores_gemma":[0.5212174,0.000001534617,0.4774231,0.00106662,0.00008888247,0.00003972221,5.981393e-7,0.000008977127,0.0001531595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5097128,"threshold_uncertainty_score":0.3688694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02680882256422215,"score_gpt":0.2456488657433482,"score_spread":0.218840043179126,"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."}}