Papers › EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers

EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers

1 May 2022ACL 2022 5archive 2025-07-28

Bugeun Kim, Kyung Seo Ki, Sangkyu Rhim, Gahgene Gweon

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.

PaperPDFCode

Code

snucclab/ept-x officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

MathMath Word Problem Solving

Datasets

Introduced by this paper, per the archive.

PEN

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Math Word Problem Solving ALG514 EPT Accuracy (%) 73.91 #6 of 10 Archive leaderboard report
Math Word Problem Solving ALG514 EPT-X Accuracy (%) 67.07 #9 of 10 Archive leaderboard report
Math Word Problem Solving DRAW-1K EPT Accuracy (%) 63.5 #1 of 5 Archive leaderboard report
Math Word Problem Solving DRAW-1K EPT-X Accuracy (%) 56 #5 of 5 Archive leaderboard report
Math Word Problem Solving MAWPS EPT Accuracy (%) 88.7 #9 of 25 Archive leaderboard report
Math Word Problem Solving MAWPS EPT-X Accuracy (%) 84.57 #13 of 25 Archive leaderboard report
Math Word Problem Solving PEN EPT-X Accuracy (%) 69.59 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections