Towards Better Quantity Representations for Solving Math Word Problems
Authors: 
Runxin Sun, Shizhu He, Jun Zhao, Kang LiuAuthors Info & Claims
Runxin Sun, Shizhu He, Jun Zhao, Kang LiuAuthors Info & ClaimsArticle No.: 96, Pages 1 - 18
Abstract
Solving a math word problem requires selecting quantities in it and performing appropriate arithmetic operations to obtain the answer. For deep learning-based methods, it is vital to obtain good quantity representations, i.e., to selectively and emphatically aggregate information in the context of quantities. However, existing works have not paid much attention to this aspect. Many works simply encode quantities as ordinary tokens, or use some implicit or rule-based methods to select information in their context. This leads to poor results when dealing with linguistic variations and confounding quantities. This article proposes a novel method to identify question-related distinguishing features of quantities by contrasting their context with the question and the context of other quantities, thereby enhancing the representation of quantities. Our method not only considers the contrastive relationship between quantities but also considers multiple relationships jointly. Besides, we propose two auxiliary tasks to further guide the representation learning of quantities: (1) predicting whether a quantity is used in the question and (2) predicting the relations (operators) between quantities given the question. Experimental results show that our method outperforms previous methods on SVAMP and ASDiv-A under similar settings, even some newly released strong baselines. Supplementary experiments further confirm that our method indeed improves the performance of quantity selection by improving the representation of both quantities and questions.
References
[1]
Daniel G. Bobrow. 1968. Natural language input for a computer problem-solving system. In Semantic Information Processing, Marvin L. Minsky (Ed.). MIT Press, 146–226.
[2]
Eugene Charniak. 1969. Computer solution of calculus word problems. In Proceedings of the 1st International Joint Conference on Artificial Intelligence. 303–316.
[3]
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171–4186.
[4]
Shizhe Diao, Pengcheng Wang, Yong Lin, and Tong Zhang. 2023. Active prompting with chain-of-thought for large language models. Retrieved from https://arXiv:2302.12246
[5]
Zhibin Gou, Zhihong Shao, Yeyun Gong, Yujiu Yang, Minlie Huang, Nan Duan, Weizhu Chen et al. 2023. Tora: A tool-integrated reasoning agent for mathematical problem solving. Retrieved from https://arXiv:2309.17452
[6]
Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman. 2014. Learning to solve arithmetic word problems with verb categorization. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 523–533.
[7]
Zhanming Jie, Jierui Li, and Wei Lu. 2022. Learning to reason deductively: Math word problem solving as complex relation extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 5944–5955.
[8]
Jb. Kim, Hazel Kim, Joonghyuk Hahn, and Yo-Sub Han. 2023. ATHENA: Mathematical reasoning with thought expansion. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). Association for Computational Linguistics, Singapore, 16315–16327. DOI:
[9]
Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. In Proceedings of the 35th International Conference on Neural Information Processing Systems. 22199–22213.
[10]
Rik Koncel-Kedziorski, Subhro Roy, Aida Amini, Nate Kushman, and Hannaneh Hajishirzi. 2016. MAWPS: A math word problem repository. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1152–1157.
[11]
Vivek Kumar, Rishabh Maheshwary, and Vikram Pudi. 2022. Practice makes a solver perfect: Data augmentation for math word problem solvers. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4194–4206.
[12]
Nate Kushman, Yoav Artzi, Luke Zettlemoyer, and Regina Barzilay. 2014. Learning to automatically solve algebra word problems. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. 271–281.
[13]
Yunshi Lan, Lei Wang, Jing Jiang, and Ee-Peng Lim. 2022. Improving compositional generalization in math word problem solving. Retrieved from https://arXiv:2209.01352
[14]
Yihuai Lan, Lei Wang, Qiyuan Zhang, Yunshi Lan, Bing Tian Dai, Yan Wang, Dongxiang Zhang, and Ee-Peng Lim. 2022. Mwptoolkit: An open-source framework for deep learning-based math word problem solvers. In Proceedings of the 36th AAAI Conference on Artificial Intelligence. 13188–13190.
[15]
Jierui Li, Lei Wang, Jipeng Zhang, Yan Wang, Bing Tian Dai, and Dongxiang Zhang. 2019. Modeling intra-relation in math word problems with different functional multi-head attentions. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 6162–6167.
[16]
Zhenwen Liang, Jipeng Zhang, Lei Wang, Wei Qin, Yunshi Lan, Jie Shao, and Xiangliang Zhang. 2022. MWP-BERT: Numeracy-augmented pre-training for math word problem solving. In Proceedings of the Association for Computational Linguistics (NAACL’22). 997–1009.
[17]
Zhenwen Liang, Jipeng Zhang, Lei Wang, Yan Wang, Jie Shao, and Xiangliang Zhang. 2022. Generalizing math word problem solvers via solution diversification. In Proceedings of the 37th AAAI Conference on Artificial Intelligence. 13183–13191.
[18]
Zhenwen Liang, Jipeng Zhang, and Xiangliang Zhang. 2022. Analogical math word problems solving with enhanced problem-solution association. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 9454–9464.
[19]
Xin Lin, Zhenya Huang, Hongke Zhao, Enhong Chen, Qi Liu, Hao Wang, and Shijin Wang. 2021. Hms: A hierarchical solver with dependency-enhanced understanding for math word problem. In Proceedings of the 35th AAAI Conference on Artificial Intelligence. 4232–4240.
[20]
Qian Liu, Dejian Yang, Jiahui Zhang, Jiaqi Guo, Bin Zhou, and Jian-Guang Lou. 2021. Awakening latent grounding from pretrained language models for semantic parsing. In Proceedings of the Association for Computational Linguistics (ACL-IJCNLP’21). 1174–1189.
[21]
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. Retrieved from https://arXiv:1907.11692
[22]
Yaojie Lu, Hongyu Lin, Xianpei Han, and Le Sun. 2019. Distilling discrimination and generalization knowledge for event detection via delta-representation learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 4366–4376.
[23]
Shen-Yun Miao, Chao-Chun Liang, and Keh-Yih Su. 2020. A diverse corpus for evaluating and developing english math word problem solvers. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 975–984.
[24]
Arindam Mitra and Chitta Baral. 2016. Learning to use formulas to solve simple arithmetic problems. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2144–2153.
[25]
Ansong Ni, Jeevana Priya Inala, Chenglong Wang, Alex Polozov, Christopher Meek, Dragomir Radev, and Jianfeng Gao. [n.d.]. Learning math reasoning from self-sampled correct and partially-correct solutions. In Proceedings of the 11th International Conference on Learning Representations.
[26]
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga et al. 2019. Pytorch: An imperative style, high-performance deep learning library. In Proceedings of the 32nd International Conference on Neural Information Processing Systems.
[27]
Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 2021. Are NLP models really able to solve simple math word problems? In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2080–2094.
[28]
Subhro Roy and Dan Roth. 2018. Mapping to declarative knowledge for word problem solving. Trans. Assoc. Comput. Linguist. 6 (2018), 159–172.
[29]
Zhihong Shao, Fei Huang, and Minlie Huang. 2022. Chaining simultaneous thoughts for numerical reasoning. In Proceedings of the Association for Computational Linguistics (EMNLP’22). 2533–2547.
[30]
Yibin Shen and Cheqing Jin. 2020. Solving math word problems with multi-encoders and multi-decoders. In Proceedings of the 28th International Conference on Computational Linguistics. 2924–2934.
[31]
Yibin Shen, Qianying Liu, Zhuoyuan Mao, Fei Cheng, and Sadao Kurohashi. 2022. Textual enhanced contrastive learning for solving math word problems. In Proceedings of the Association for Computational Linguistics (EMNLP’22). 4297–4307.
[32]
Shuming Shi, Yuehui Wang, Chin-Yew Lin, Xiaojiang Liu, and Yong Rui. 2015. Automatically solving number word problems by semantic parsing and reasoning. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 1132–1142.
[33]
Minghuan Tan, Lei Wang, Lingxiao Jiang, and Jing Jiang. 2021. Investigating math word problems using pretrained multilingual language models. Retrieved from https://arXiv:2105.08928
[34]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 30th International Conference on Neural Information Processing Systems.
[35]
Bin Wang, Jiangzhou Ju, Yang Fan, Xinyu Dai, Shujian Huang, and Jiajun Chen. 2022. Structure-unified M-tree coding solver for math word problem. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 8122–8132.
[36]
Tianduo Wang and Wei Lu. 2023. Learning multi-step reasoning by solving arithmetic tasks. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 1229–1238.
[37]
Yan Wang, Xiaojiang Liu, and Shuming Shi. 2017. Deep neural solver for math word problems. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 845–854.
[38]
Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz et al. 2020. Transformers: State-of-the-art natural language processing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 38–45.
[39]
Qinzhuo Wu, Qi Zhang, Jinlan Fu, and Xuan-Jing Huang. 2020. A knowledge-aware sequence-to-tree network for math word problem solving. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 7137–7146.
[40]
Qinzhuo Wu, Qi Zhang, and Zhongyu Wei. 2021. An edge-enhanced hierarchical graph-to-tree network for math word problem solving. In Proceedings of the Association for Computational Linguistics (EMNLP’21). 1473–1482.
[41]
Qinzhuo Wu, Qi Zhang, Zhongyu Wei, and Xuan-Jing Huang. 2021. Math word problem solving with explicit numerical values. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 5859–5869.
[42]
Zhipeng Xie and Shichao Sun. 2019. A goal-driven tree-structured neural model for math word problems. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’19). 5299–5305.
[43]
Weijiang Yu, Yingpeng Wen, Fudan Zheng, and Nong Xiao. 2021. Improving math word problems with pre-trained knowledge and hierarchical reasoning. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. 3384–3394.
[44]
Jipeng Zhang, Lei Wang, Roy Ka-Wei Lee, Yi Bin, Yan Wang, Jie Shao, and Ee-Peng Lim. 2020. Graph-to-tree learning for solving math word problems. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 3928–3937.
[45]
Wenqi Zhang, Yongliang Shen, Yanna Ma, Xiaoxia Cheng, Zeqi Tan, Qingpeng Nong, and Weiming Lu. 2022. Multi-view reasoning: Consistent contrastive learning for math word problem. In Proceedings of the Association for Computational Linguistics (EMNLP’22). 1103–1116.
[46]
Wenqi Zhang, Yongliang Shen, Qingpeng Nong, Zeqi Tan, Yanna Ma, and Weiming Lu. 2023. An expression tree decoding strategy for mathematical equation generation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). Association for Computational Linguistics, Singapore, 439–456. DOI:
[47]
Yanyan Zou and Wei Lu. 2019. Text2Math: End-to-end parsing text into math expressions. In Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 5327–5337.
Index Terms
- Towards Better Quantity Representations for Solving Math Word Problems
Recommendations
Number-enhanced representation with hierarchical recursive tree decoding for math word problem solving
AbstractAutomatic solving math word problems (MWPs) is a number-intensive application in natural language processing (NLP). However, these existing methods are far from achieving acceptable levels of numeracy learning. As a result, the performance of ...
Highlights- We propose a number-enhanced representation framework to model numbers and relations.
- We devise a new tree-structured decoder to address early-stage information loss.
- We outperform the state-of-the-art baselines on four benchmark ...
Reduced models for solving particle beams and plasma physics problems
MATH'08: Proceedings of the American Conference on Applied MathematicsIn recent years, modelling and solving numerically problems which couple charged particle to electro-magnetic fields has given rise to challenging mathematical and scientific computing developments. In the industry, a variety of examples can be thought ...
Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving
AbstractMath Word Problem (MWP) solving presents a challenging task in Natural Language Processing (NLP). This study aims to provide MWP solvers with a more diverse training set, ultimately improving their ability to solve various math problems. We ...
Comments
Information & Contributors
Information
Published In
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 26 June 2024
Online AM: 18 May 2024
Accepted: 27 April 2024
Revised: 04 February 2024
Received: 07 August 2023
Published in TALLIP Volume 23, Issue 7
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Key R&D Program of China
- National Natural Science Foundation of China
- Youth Innovation Promotion Association CAS
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 168Total Downloads
- Downloads (Last 12 months)168
- Downloads (Last 6 weeks)9
Reflects downloads up to 02 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in