{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001126903,0.001172923,0.0006500234,0.0005413549,0.0005824771,0.0006894473,0.001461068,0.00169723,0.004071419],"category_scores_gemma":[0.005132879,0.0004527211,0.0006985921,0.0004883217,0.0006294642,0.00249888,0.00154367,0.002471271,0.001156332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001123801,"about_ca_system_score_gemma":0.001326996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005690281,"about_ca_topic_score_gemma":0.01429978,"domain_scores_codex":[0.9994947,0.000195351,0.00002164866,0.0001779604,0.00005583498,0.00005446661],"domain_scores_gemma":[0.9987081,0.0008287902,0.0000726457,0.0001408049,0.0001652777,0.00008437946],"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":[0.0006114167,0.0003445706,0.004799159,0.0002494986,0.000107105,0.0002620037,0.0003943048,0.6272885,0.007198429,0.01437828,0.008706624,0.3356601],"study_design_scores_gemma":[0.00002086917,0.00004242631,0.0001168481,0.000006484184,0.0000122383,0.00002273771,0.00003021576,0.990973,0.001689676,0.006366475,0.0007143201,0.000004778994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.222829,0.001197081,0.7567205,0.002137111,0.0001933503,0.0002329085,0.0006572836,0.003678145,0.01235461],"genre_scores_gemma":[0.8274302,0.0002952509,0.1604327,0.0004937671,0.0001049443,0.0002857108,0.001573414,0.0002199178,0.009164114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005690281,"threshold_uncertainty_score":0.01362026,"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."}}