{"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/ept-x-an-expression-pointer-transformer-model","title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","arxiv_id":null,"date":"2022-05-01","proceeding":"ACL 2022 5","authors":["Bugeun Kim","Kyung Seo Ki","Sangkyu Rhim","Gahgene Gweon"],"abstract":"In this paper, we propose a neural model EPT-X (Expression-Pointer Transformer with Explanations), which utilizes natural language explanations to solve an algebraic word problem. To enhance the explainability of the encoding process of a neural model, EPT-X adopts the concepts of plausibility and faithfulness which are drawn from math word problem solving strategies by humans. A plausible explanation is one that includes contextual information for the numbers and variables that appear in a given math word problem. A faithful explanation is one that accurately represents the reasoning process behind the model’s solution equation. The EPT-X model yields an average baseline performance of 69.59% on our PEN dataset and produces explanations with quality that is comparable to human output. The contribution of this work is two-fold. (1) EPT-X model: An explainable neural model that sets a baseline for algebraic word problem solving task, in terms of model’s correctness, plausibility, and faithfulness. (2) New dataset: We release a novel dataset PEN (Problems with Explanations for Numbers), which expands the existing datasets by attaching explanations to each number/variable.","url_abs":"https://aclanthology.org/2022.acl-long.305","url_pdf":"https://aclanthology.org/2022.acl-long.305.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":"ept-x-an-expression-pointer-transformer-model","repo_url":"https://github.com/snucclab/ept-x","is_official":1,"mentioned_in_paper":1,"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":[],"datasets_introduced":[{"slug":"pen","name":"PEN","full_name":"Problems with Explanations for Numbers"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/math-word-problem-solving-on-alg514","task":"Math Word Problem Solving","dataset":"ALG514","model":"EPT","rank_in_archive_order":6,"of":10,"metrics":{"Accuracy (%)":"73.91"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-alg514","task":"Math Word Problem Solving","dataset":"ALG514","model":"EPT-X","rank_in_archive_order":9,"of":10,"metrics":{"Accuracy (%)":"67.07"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-draw-1k","task":"Math Word Problem Solving","dataset":"DRAW-1K","model":"EPT","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy (%)":"63.5"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-draw-1k","task":"Math Word Problem Solving","dataset":"DRAW-1K","model":"EPT-X","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy (%)":"56"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-mawps","task":"Math Word Problem Solving","dataset":"MAWPS","model":"EPT","rank_in_archive_order":9,"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":"EPT-X","rank_in_archive_order":13,"of":25,"metrics":{"Accuracy (%)":"84.57"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-pen","task":"Math Word Problem Solving","dataset":"PEN","model":"EPT-X","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"69.59"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}