![]() ![]() In this paper, we restrict our attention to English MWPs taught in grades four and lower. Cite (Informal): Are NLP Models really able to Solve Simple Math Word Problems? (Patel et al., NAACL 2021) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Optional supplementary code:Ģ圜ode.zip Optional supplementary data:Ģ.zip Video: Code arkilpatel/SVAMPĪdditional community code Data SVAMP, MAWPS, = "Are with the bulk of research attention moving to more complex MWPs. Association for Computational Linguistics. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2080–2094, Online. Are NLP Models really able to Solve Simple Math Word Problems?. Anthology ID: 2021.naacl-main.168 Volume: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Month: June Year: 2021 Address: Online Venue: NAACL SIG: Publisher: Association for Computational Linguistics Note: Pages: 2080–2094 Language: URL: DOI: 10.18653/v1/2021.naacl-main.168 Bibkey: patel-etal-2021-nlp Cite (ACL): Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 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. Further, we introduce a challenge dataset, SVAMP, created by applying carefully chosen variations over examples sampled from existing datasets. Similarly, models that treat MWPs as bag-of-words can also achieve surprisingly high accuracy. 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. We provide strong evidence that the existing MWP solvers rely on shallow heuristics to achieve high performance on the benchmark datasets. 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. Abstract The problem of designing NLP solvers for math word problems (MWP) has seen sustained research activity and steady gains in the test accuracy. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |