Knowledge Commons of Institute of Automation,CAS
Towards Better Quantity Representations for Solving Math Word Problems | |
Sun, Runxin1,2; He, Shizhu1,2; Zhao, Jun1,2; Liu, Kang1,2,3 | |
发表期刊 | ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP) |
2024-05 | |
页码 | - |
摘要 | 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 paper 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; 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. |
收录类别 | SCI |
语种 | 英语 |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 语音语言处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56605 |
专题 | 复杂系统认知与决策实验室 |
通讯作者 | Liu, Kang |
作者单位 | 1.The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, China 3.Shanghai Artificial Intelligence Laboratory, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Sun, Runxin,He, Shizhu,Zhao, Jun,et al. Towards Better Quantity Representations for Solving Math Word Problems[J]. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP),2024:-. |
APA | Sun, Runxin,He, Shizhu,Zhao, Jun,&Liu, Kang.(2024).Towards Better Quantity Representations for Solving Math Word Problems.ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP),-. |
MLA | Sun, Runxin,et al."Towards Better Quantity Representations for Solving Math Word Problems".ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP) (2024):-. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
3665644.pdf(417KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论