Yiyao Li, Lu Wang, Jung Jae Kim, Chor Seng Tan, & Ye Luo. (2024). On the Selection of Positive and Negative Samples for Contrastive Math Word Problem Neural Solver. Proceedings of the 17th International Conference on Educational Data Mining, 96-106. https://doi.org/10.5281/zenodo.12729780
Abstract:
Solving math word problems (MWPs) involves uncovering
logical relationships among quantities in natural language
descriptions of math problems. Recent studies have demonstrated that the contrastive learning framework can assist
models in identifying semantically similar examples while
distinguishing between different mathematical logics. This
alleviates models’ dependence on shallow heuristics for predicting problem solutions. However, we have observed significant disparities in the positive and negative sample selections among different contrastive learning frameworks,
which can sometimes exhibit complete contradictions. This
discrepancy is attributed to the lack of an effective criterion
for evaluating the distance between the mathematical logics of word problems. To address this issue, we introduce a
novel formula for evaluating mathematical equation similarity in the context of word problem association. Our formula
enables flexible focus on either global or local differences in
the mathematical logic, thereby implementing distinct criteria for similarity calculation. We investigate the impact of
various positive and negative sample selection strategies on
contrastive learning models using the proposed formula in
order to identify the optimal strategy. Our experimental
results reveal substantial performance improvements over
existing baselines, highlighting the effectiveness of our approach
License type:
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Funding Info:
This research / project is supported by the MOE - Science of learning
Grant Reference no. : MOE-MOESOL2021-0006