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

Creative Commons License

Yigit G., AMASYALI M. F.

SN Computer Science, cilt.5, sa.5, 2024 (Scopus) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 5 Sayı: 5
  • Basım Tarihi: 2024
  • Doi Numarası: 10.1007/s42979-024-02853-x
  • Dergi Adı: SN Computer Science
  • Derginin Tarandığı İndeksler: Scopus
  • Anahtar Kelimeler: Data augmentation, In-context learning, Llama-7b, Math word problem solving, Question answering
  • Yıldız Teknik Üniversitesi Adresli: Evet

Özet

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.