Abstract
Solving math word problems depends on how to articulate the problems, the lens through which models view human linguistic expressions. Real-world settings count on such a method even more due to the diverse practices of the same mathematical operations. Earlier works constrain available thinking processes by limited prediction strategies without considering their significance in acquiring mathematical knowledge. We introduce Attention-based THought Expansion Network Architecture (ATHENA) to tackle the challenges of real-world practices by mimicking human thought expansion mechanisms in the form of neural network propagation. A thought expansion recurrently generates the candidates carrying the thoughts of possible math expressions driven from the previous step and yields reasonable thoughts by selecting the valid pathways to the goal. Our experiments show that ATHENA achieves a new state-of-the-art stage toward the ideal model that is compelling in variant questions even when the informativeness in training examples is restricted.- Anthology ID:
- 2023.emnlp-main.1014
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 16315–16327
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.1014
- DOI:
- 10.18653/v1/2023.emnlp-main.1014
- Cite (ACL):
- Jb. Kim, Hazel Kim, Joonghyuk Hahn, and Yo-Sub Han. 2023. ATHENA: Mathematical Reasoning with Thought Expansion. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16315–16327, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- ATHENA: Mathematical Reasoning with Thought Expansion (Kim et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.emnlp-main.1014.pdf
- Code
- the-jb/athena-math
- Data
- ASDiv, MAWPS, Math23K, SVAMP