Noun-MWP: Math Word Problems Meet Noun Answers

Taehun Cha, Jaeheun Jung, Donghun Lee


Abstract
We introduce a new type of problems for math word problem (MWP) solvers, named Noun-MWPs, whose answer is a non-numerical string containing a noun from the problem text. We present a novel method to empower existing MWP solvers to handle Noun-MWPs, and apply the method on Expression-Pointer Transformer (EPT). Our model, N-EPT, solves Noun-MWPs significantly better than other models, and at the same time, solves conventional MWPs as well. Solving Noun-MWPs may lead to bridging MWP solvers and traditional question-answering NLP models.
Anthology ID:
2022.coling-1.338
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
3847–3857
Language:
URL:
https://aclanthology.org/2022.coling-1.338
DOI:
Bibkey:
Cite (ACL):
Taehun Cha, Jaeheun Jung, and Donghun Lee. 2022. Noun-MWP: Math Word Problems Meet Noun Answers. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3847–3857, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Noun-MWP: Math Word Problems Meet Noun Answers (Cha et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.338.pdf
Data
MAWPS