{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004715994,0.001083629,0.0005487867,0.0008492553,0.0003677045,0.0006318731,0.001081131,0.001031375,0.004905694],"category_scores_gemma":[0.003281821,0.0002728421,0.00084077,0.001573144,0.0005479457,0.002634093,0.0007299908,0.002083915,0.001386475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009836101,"about_ca_system_score_gemma":0.001061056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005504417,"about_ca_topic_score_gemma":0.01314849,"domain_scores_codex":[0.9997026,0.00009437916,0.00001923825,0.00009664475,0.00006366396,0.00002345676],"domain_scores_gemma":[0.9994397,0.000380651,0.00004314327,0.00004850982,0.00006514097,0.00002289057],"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":[0.0001148134,0.000236601,0.001110411,0.000692629,0.00007206386,0.0001358732,0.0002832492,0.3295096,0.005258049,0.0579388,0.02979947,0.5748485],"study_design_scores_gemma":[0.00002502651,0.00003505183,0.0001188767,0.00002161316,0.00001145207,0.0000161004,0.00003540145,0.9280442,0.001203764,0.06703949,0.003441805,0.000007149036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04001089,0.001621926,0.9440437,0.001084164,0.0001370411,0.0001843088,0.001280603,0.004915055,0.006722379],"genre_scores_gemma":[0.3652425,0.001515445,0.6169407,0.0006309066,0.0001484688,0.0004782447,0.006416954,0.0005666742,0.008060124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005504417,"threshold_uncertainty_score":0.01641119,"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."}}