A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yi, Zhou, Guangyou, Xie, Zhiwen, Ma, Jinjin, Huang, Jimmy Xiangji
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909450473832448
author Zhang, Yi
Zhou, Guangyou
Xie, Zhiwen
Ma, Jinjin
Huang, Jimmy Xiangji
author_facet Zhang, Yi
Zhou, Guangyou
Xie, Zhiwen
Ma, Jinjin
Huang, Jimmy Xiangji
contents Math Word Problem (MWP) solving is a critical task in natural language processing, has garnered significant research interest in recent years. Various recent studies heavily rely on Seq2Seq models and their extensions (e.g., Seq2Tree and Graph2Tree) to generate mathematical equations. While effective, these models struggle to generate diverse but counterpart solution equations, limiting their generalization across various math problem scenarios. In this paper, we introduce a novel Diversity-enhanced Knowledge Distillation (DivKD) model for practical MWP solving. Our approach proposes an adaptive diversity distillation method, in which a student model learns diverse equations by selectively transferring high-quality knowledge from a teacher model. Additionally, we design a diversity prior-enhanced student model to better capture the diversity distribution of equations by incorporating a conditional variational auto-encoder. Extensive experiments on {four} MWP benchmark datasets demonstrate that our approach achieves higher answer accuracy than strong baselines while maintaining high efficiency for practical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03670
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving
Zhang, Yi
Zhou, Guangyou
Xie, Zhiwen
Ma, Jinjin
Huang, Jimmy Xiangji
Computation and Language
Artificial Intelligence
Math Word Problem (MWP) solving is a critical task in natural language processing, has garnered significant research interest in recent years. Various recent studies heavily rely on Seq2Seq models and their extensions (e.g., Seq2Tree and Graph2Tree) to generate mathematical equations. While effective, these models struggle to generate diverse but counterpart solution equations, limiting their generalization across various math problem scenarios. In this paper, we introduce a novel Diversity-enhanced Knowledge Distillation (DivKD) model for practical MWP solving. Our approach proposes an adaptive diversity distillation method, in which a student model learns diverse equations by selectively transferring high-quality knowledge from a teacher model. Additionally, we design a diversity prior-enhanced student model to better capture the diversity distribution of equations by incorporating a conditional variational auto-encoder. Extensive experiments on {four} MWP benchmark datasets demonstrate that our approach achieves higher answer accuracy than strong baselines while maintaining high efficiency for practical applications.
title A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2501.03670