{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/are-nlp-models-really-able-to-solve-simple","title":"Are NLP Models really able to Solve Simple Math Word Problems?","arxiv_id":"2103.07191","date":"2021-03-12","proceeding":"NAACL 2021 4","authors":["Arkil Patel","Satwik Bhattamishra","Navin Goyal"],"abstract":"The problem of designing NLP solvers for math word problems (MWP) has seen sustained research activity and steady gains in the test accuracy. Since existing solvers achieve high performance on the benchmark datasets for elementary level MWPs containing one-unknown arithmetic word problems, such problems are often considered \"solved\" with the bulk of research attention moving to more complex MWPs. In this paper, we restrict our attention to English MWPs taught in grades four and lower. We provide strong evidence that the existing MWP solvers rely on shallow heuristics to achieve high performance on the benchmark datasets. To this end, we show that MWP solvers that do not have access to the question asked in the MWP can still solve a large fraction of MWPs. Similarly, models that treat MWPs as bag-of-words can also achieve surprisingly high accuracy. Further, we introduce a challenge dataset, SVAMP, created by applying carefully chosen variations over examples sampled from existing datasets. The best accuracy achieved by state-of-the-art models is substantially lower on SVAMP, thus showing that much remains to be done even for the simplest of the MWPs.","url_abs":"https://arxiv.org/abs/2103.07191v2","url_pdf":"https://arxiv.org/pdf/2103.07191v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"are-nlp-models-really-able-to-solve-simple","repo_url":"https://github.com/arkilpatel/SVAMP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"are-nlp-models-really-able-to-solve-simple","repo_url":"https://github.com/debjitpaul/refiner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"are-nlp-models-really-able-to-solve-simple","repo_url":"https://github.com/vedantgaur/symbolic-mwp-reasoning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"math","task_name":"Math"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"},{"task_slug":"math-word-problem-solvingo","task_name":"Math Word Problem SolvingΩ"}],"methods":[{"method_slug":"gts","method_name":"GTS"},{"method_slug":"graph2tree","method_name":"Graph2Tree"}],"datasets_introduced":[{"slug":"svamp","name":"SVAMP","full_name":"Simple Variations on Arithmetic Math word Problems"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/math-word-problem-solving-on-asdiv-a","task":"Math Word Problem Solving","dataset":"ASDiv-A","model":"Graph2Tree with RoBERTa","rank_in_archive_order":6,"of":9,"metrics":{"Execution Accuracy":"82.2"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-asdiv-a","task":"Math Word Problem Solving","dataset":"ASDiv-A","model":"GTS with RoBERTa","rank_in_archive_order":7,"of":9,"metrics":{"Execution Accuracy":"81.2"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-asdiv-a","task":"Math Word Problem Solving","dataset":"ASDiv-A","model":"LSTM Seq2Seq with RoBERTa","rank_in_archive_order":9,"of":9,"metrics":{"Execution Accuracy":"76.9"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-mawps","task":"Math Word Problem Solving","dataset":"MAWPS","model":"Graph2Tree with RoBERTa","rank_in_archive_order":10,"of":25,"metrics":{"Accuracy (%)":"88.7"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-mawps","task":"Math Word Problem Solving","dataset":"MAWPS","model":"GTS with RoBERTa","rank_in_archive_order":11,"of":25,"metrics":{"Accuracy (%)":"88.5"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-svamp","task":"Math Word Problem Solving","dataset":"SVAMP","model":"Graph2Tree with RoBERTa","rank_in_archive_order":21,"of":26,"metrics":{"Accuracy":"43.8","Execution Accuracy":"43.8"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-svamp","task":"Math Word Problem Solving","dataset":"SVAMP","model":"GTS with RoBERTa","rank_in_archive_order":22,"of":26,"metrics":{"Accuracy":"41.0","Execution Accuracy":"41.0"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-svamp","task":"Math Word Problem Solving","dataset":"SVAMP","model":"LSTM Seq2Seq with RoBERTa","rank_in_archive_order":23,"of":26,"metrics":{"Accuracy":"40.3","Execution Accuracy":"40.3"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-svamp","task":"Math Word Problem Solving","dataset":"SVAMP","model":"Transformer with RoBERTa","rank_in_archive_order":25,"of":26,"metrics":{"Accuracy":"38.9","Execution Accuracy":"38.9"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2103.07191","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}