{"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/an-expression-tree-decoding-strategy-for","title":"An Expression Tree Decoding Strategy for Mathematical Equation Generation","arxiv_id":"2310.09619","date":"2023-10-14","proceeding":null,"authors":["Wenqi Zhang","Yongliang Shen","Qingpeng Nong","Zeqi Tan","Yanna Ma","Weiming Lu"],"abstract":"Generating mathematical equations from natural language requires an accurate understanding of the relations among math expressions. Existing approaches can be broadly categorized into token-level and expression-level generation. The former treats equations as a mathematical language, sequentially generating math tokens. Expression-level methods generate each expression one by one. However, each expression represents a solving step, and there naturally exist parallel or dependent relations between these steps, which are ignored by current sequential methods. Therefore, we integrate tree structure into the expression-level generation and advocate an expression tree decoding strategy. To generate a tree with expression as its node, we employ a layer-wise parallel decoding strategy: we decode multiple independent expressions (leaf nodes) in parallel at each layer and repeat parallel decoding layer by layer to sequentially generate these parent node expressions that depend on others. Besides, a bipartite matching algorithm is adopted to align multiple predictions with annotations for each layer. Experiments show our method outperforms other baselines, especially for these equations with complex structures.","url_abs":"https://arxiv.org/abs/2310.09619v3","url_pdf":"https://arxiv.org/pdf/2310.09619v3.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":"an-expression-tree-decoding-strategy-for","repo_url":"https://github.com/zwq2018/multi-view-consistency-for-mwp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"math","task_name":"Math"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/math-word-problem-solving-on-mawps","task":"Math Word Problem Solving","dataset":"MAWPS","model":"Exp-Tree","rank_in_archive_order":5,"of":25,"metrics":{"Accuracy (%)":"92.3"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math23k","task":"Math Word Problem Solving","dataset":"Math23K","model":"Exp-Tree","rank_in_archive_order":4,"of":19,"metrics":{"Accuracy (5-fold)":"84.1","Accuracy (training-test)":"86.2"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-mathqa","task":"Math Word Problem Solving","dataset":"MathQA","model":"Exp-Tree","rank_in_archive_order":2,"of":5,"metrics":{"Answer Accuracy":"81.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.09619","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}