{"id":"W3035498813","doi":"10.18653/v1/2020.acl-main.362","title":"Graph-to-Tree Learning for Solving Math Word Problems","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China; National Research Foundation","keywords":"Computer science; Benchmark (surveying); Graph; Encoder; Tree (set theory); Theoretical computer science; Artificial intelligence; Machine learning; Algorithm; Mathematics; Combinatorics","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":[0.0001506444,0.00008497311,0.0001044048,0.00004404586,0.0001025103,0.00015047,0.0005484293,0.00002731164,0.000008376957],"category_scores_gemma":[0.00008212923,0.00007592815,0.00005298256,0.0002441411,0.000005027166,0.0002187099,0.0002562109,0.00009890133,0.0000534418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001013038,"about_ca_system_score_gemma":0.00002315496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001328011,"about_ca_topic_score_gemma":0.0000113929,"domain_scores_codex":[0.9990919,0.00001004013,0.0001531908,0.0003579584,0.0001368326,0.0002501344],"domain_scores_gemma":[0.9995421,0.00005375802,0.00003304154,0.0001974882,0.00004077395,0.0001328692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009782596,0.00003241692,0.002335855,0.0001624328,0.00003199545,0.000007299281,0.01123414,0.1189075,0.01086142,0.3591677,0.00351598,0.4937335],"study_design_scores_gemma":[0.0001433236,0.00006746189,0.0001137873,0.00001560954,0.000001794907,0.000001181965,0.00004748116,0.9839138,0.0004322271,0.002867325,0.01227068,0.000125347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008585392,0.00002527805,0.9814634,0.007113713,0.0001090961,0.0002441525,1.029682e-7,0.000393438,0.002065481],"genre_scores_gemma":[0.5687505,0.000001499224,0.4288516,0.001715125,0.0000910438,0.00002807797,4.164032e-7,0.000008663184,0.0005530054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8650063,"threshold_uncertainty_score":0.309626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04213538154258915,"score_gpt":0.241774129357678,"score_spread":0.1996387478150888,"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."}}