Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solving

No Thumbnail Available

Date

2024

Journal Title

Journal ISSN

Volume Title

Publisher

Springer

Research Projects

Organizational Units

Journal Issue

Abstract

Math 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 propose several methods for data augmentation by modifying the problem texts and equations, such as synonym replacement, rule-based: question replacement, and rule based: reversing question methodologies over two English MWP datasets. This study extends by introducing a new in-context learning augmentation method, employing the Llama-7b language model. This approach involves instruction-based prompting for rephrasing the math problem texts. Performance evaluations are conducted on 9 baseline models, revealing that augmentation methods outperform baseline models. Moreover, concatenating examples generated by various augmentation methods further improves performance. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

Description

Keywords

Data augmentation, In-context learning, Llama-7b, Math word problem solving, Question answering

Turkish CoHE Thesis Center URL

Citation

0

WoS Q

N/A

Scopus Q

Q2

Source

SN Computer Science

Volume

5

Issue

5

Start Page

End Page