Solving Math Word Problems Following Logically Consistent Template

Zeyu Huang; Xiaofeng Zhang; Jun Bai; Wenge Rong; Yuanxin Ouyang; Zhang Xiong

doi:10.1109/IJCNN54540.2023.10191776

Solving Math Word Problems Following Logically Consistent Template

Zeyu Huang
, Xiaofeng Zhang
, Jun Bai
, Wenge Rong
, Yuanxin Ouyang
, Zhang Xiong

School of Computer Science and Engineering

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Solving math word problems (MWPs) is a challenging task. Some existing solvers retrieve textually similar problems and draw on their solutions to solve the given problem. However, textually similar questions are not guaranteed to have similar solutions, and vice versa. Therefore, this work investigates the logical consistency among different problems and proposes a novel framework to solve math word problems following logically consistent templates. Experimental results show that our method outperforms many strong baselines, including some pre-trained language model-based methods. Further analysis shows that our retrieval method does learn the logical similarity between Questions and plays a crucial role in our model's nerformance.

Original language	English
Title of host publication	IJCNN 2023 - International Joint Conference on Neural Networks, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665488679
DOIs	https://doi.org/10.1109/IJCNN54540.2023.10191776
State	Published - 2023
Event	2023 International Joint Conference on Neural Networks, IJCNN 2023 - Gold Coast, Australia Duration: 18 Jun 2023 → 23 Jun 2023

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2023-June

Conference

Conference	2023 International Joint Conference on Neural Networks, IJCNN 2023
Country/Territory	Australia
City	Gold Coast
Period	18/06/23 → 23/06/23

Keywords

Contrastive Learning
Math Word Problems
Natural Language Processing

Access to Document

10.1109/IJCNN54540.2023.10191776

Cite this

Huang, Z., Zhang, X., Bai, J., Rong, W., Ouyang, Y., & Xiong, Z. (2023). Solving Math Word Problems Following Logically Consistent Template. In IJCNN 2023 - International Joint Conference on Neural Networks, Proceedings (Proceedings of the International Joint Conference on Neural Networks; Vol. 2023-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN54540.2023.10191776

@inproceedings{f8c5d1fca69f4503b1bd9565b11847ac,

title = "Solving Math Word Problems Following Logically Consistent Template",

abstract = "Solving math word problems (MWPs) is a challenging task. Some existing solvers retrieve textually similar problems and draw on their solutions to solve the given problem. However, textually similar questions are not guaranteed to have similar solutions, and vice versa. Therefore, this work investigates the logical consistency among different problems and proposes a novel framework to solve math word problems following logically consistent templates. Experimental results show that our method outperforms many strong baselines, including some pre-trained language model-based methods. Further analysis shows that our retrieval method does learn the logical similarity between Questions and plays a crucial role in our model's nerformance.",

keywords = "Contrastive Learning, Math Word Problems, Natural Language Processing",

author = "Zeyu Huang and Xiaofeng Zhang and Jun Bai and Wenge Rong and Yuanxin Ouyang and Zhang Xiong",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Joint Conference on Neural Networks, IJCNN 2023 ; Conference date: 18-06-2023 Through 23-06-2023",

year = "2023",

doi = "10.1109/IJCNN54540.2023.10191776",

language = "英语",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "IJCNN 2023 - International Joint Conference on Neural Networks, Proceedings",

address = "美国",

}

Huang, Z, Zhang, X, Bai, J, Rong, W , Ouyang, Y & Xiong, Z 2023, Solving Math Word Problems Following Logically Consistent Template. in IJCNN 2023 - International Joint Conference on Neural Networks, Proceedings. Proceedings of the International Joint Conference on Neural Networks, vol. 2023-June, Institute of Electrical and Electronics Engineers Inc., 2023 International Joint Conference on Neural Networks, IJCNN 2023, Gold Coast, Australia, 18/06/23. https://doi.org/10.1109/IJCNN54540.2023.10191776

Solving Math Word Problems Following Logically Consistent Template. / Huang, Zeyu; Zhang, Xiaofeng; Bai, Jun et al.
IJCNN 2023 - International Joint Conference on Neural Networks, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings of the International Joint Conference on Neural Networks; Vol. 2023-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Solving Math Word Problems Following Logically Consistent Template

AU - Huang, Zeyu

AU - Zhang, Xiaofeng

AU - Bai, Jun

AU - Rong, Wenge

AU - Ouyang, Yuanxin

AU - Xiong, Zhang

PY - 2023

Y1 - 2023

N2 - Solving math word problems (MWPs) is a challenging task. Some existing solvers retrieve textually similar problems and draw on their solutions to solve the given problem. However, textually similar questions are not guaranteed to have similar solutions, and vice versa. Therefore, this work investigates the logical consistency among different problems and proposes a novel framework to solve math word problems following logically consistent templates. Experimental results show that our method outperforms many strong baselines, including some pre-trained language model-based methods. Further analysis shows that our retrieval method does learn the logical similarity between Questions and plays a crucial role in our model's nerformance.

AB - Solving math word problems (MWPs) is a challenging task. Some existing solvers retrieve textually similar problems and draw on their solutions to solve the given problem. However, textually similar questions are not guaranteed to have similar solutions, and vice versa. Therefore, this work investigates the logical consistency among different problems and proposes a novel framework to solve math word problems following logically consistent templates. Experimental results show that our method outperforms many strong baselines, including some pre-trained language model-based methods. Further analysis shows that our retrieval method does learn the logical similarity between Questions and plays a crucial role in our model's nerformance.

KW - Contrastive Learning

KW - Math Word Problems

KW - Natural Language Processing

UR - https://www.scopus.com/pages/publications/85169591487

U2 - 10.1109/IJCNN54540.2023.10191776

DO - 10.1109/IJCNN54540.2023.10191776

M3 - 会议稿件

AN - SCOPUS:85169591487

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - IJCNN 2023 - International Joint Conference on Neural Networks, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 International Joint Conference on Neural Networks, IJCNN 2023

Y2 - 18 June 2023 through 23 June 2023

ER -

Huang Z, Zhang X, Bai J, Rong W , Ouyang Y, Xiong Z. Solving Math Word Problems Following Logically Consistent Template. In IJCNN 2023 - International Joint Conference on Neural Networks, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN54540.2023.10191776

Solving Math Word Problems Following Logically Consistent Template

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this