Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem
Wenqi Zhang, Yongliang Shen, Yanna Ma, Xiaoxia Cheng, Zeqi Tan, Qingpeng Nong, Weiming Lu
Abstract
Math word problem solver requires both precise relation reasoning about quantities in the text and reliable generation for the diverse equation. Current sequence-to-tree or relation extraction methods regard this only from a fixed view, struggling to simultaneously handle complex semantics and diverse equations. However, human solving naturally involves two consistent reasoning views: top-down and bottom-up, just as math equations also can be expressed in multiple equivalent forms: pre-order and post-order. We propose a multi-view consistent contrastive learning for a more complete semantics-to-equation mapping. The entire process is decoupled into two independent but consistent views: top-down decomposition and bottom-up construction, and the two reasoning views are aligned in multi-granularity for consistency, enhancing global generation and precise reasoning. Experiments on multiple datasets across two languages show our approach significantly outperforms the existing baselines, especially on complex problems. We also show after consistent alignment, multi-view can absorb the merits of both views and generate more diverse results consistent with the mathematical laws.
BibTeX
@inproceedings{zhang-etal-2022-multi-view,
title = "Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem",
author = "Zhang, Wenqi and
Shen, Yongliang and
Ma, Yanna and
Cheng, Xiaoxia and
Tan, Zeqi and
Nong, Qingpeng and
Lu, Weiming",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.79/",
doi = "10.18653/v1/2022.findings-emnlp.79",
pages = "1103--1116"
}