{"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/a-goal-driven-tree-structured-neural-model","title":"A Goal-Driven Tree-Structured Neural Model for Math Word Problems","arxiv_id":null,"date":"2019-08-10","proceeding":null,"authors":["Zhipeng Xie and Shichao Sun"],"abstract":"Most existing neural models for math word problems exploit Seq2Seq model to generate solution\r\nexpressions sequentially from left to right, whose\r\nresults are far from satisfactory due to the lack\r\nof goal-driven mechanism commonly seen in human problem solving. This paper proposes a treestructured neural model to generate expression tree\r\nin a goal-driven manner. Given a math word problem, the model first identifies and encodes its goal\r\nto achieve, and then the goal gets decomposed into\r\nsub-goals combined by an operator in a top-down\r\nrecursive way. The whole process is repeated until the goal is simple enough to be realized by a\r\nknown quantity as leaf node. During the process,\r\ntwo-layer gated-feedforward networks are designed\r\nto implement each step of goal decomposition, and\r\na recursive neural network is used to encode fulfilled subtrees into subtree embeddings, which provides a better representation of subtrees than the\r\nsimple goals of subtrees. Experimental results on\r\nthe dataset Math23K have shown that our treestructured model outperforms significantly several\r\nstate-of-the-art models.","url_abs":"https://www.ijcai.org/Proceedings/2019/736","url_pdf":"https://www.ijcai.org/Proceedings/2019/0736.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":"a-goal-driven-tree-structured-neural-model","repo_url":"https://github.com/ShichaoSun/math_seq2tree","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"math","task_name":"Math"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"}],"methods":[{"method_slug":"gts","method_name":"GTS"}],"datasets_introduced":[],"methods_introduced":[{"slug":"gts","name":"GTS","full_name":"Goal-Driven Tree-Structured Neural Model"}],"results":[{"leaderboard":"/sota/math-word-problem-solving-on-math23k","task":"Math Word Problem Solving","dataset":"Math23K","model":"GTS","rank_in_archive_order":13,"of":19,"metrics":{"Accuracy (5-fold)":"74.3"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}