GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning

Document Type

Conference Proceeding

Publication Title

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

Abstract

Automatic math problem solving has recently attracted increasing attention as a longstanding AI benchmark. In this paper, we focus on solving geometric problems, which requires a comprehensive understanding of textual descriptions, visual diagrams, and theorem knowledge. However, the existing methods were highly dependent on handcraft rules and were merely evaluated on small-scale datasets. Therefore, we propose a Geometric Question Answering dataset GeoQA, containing 5,010 geometric problems with corresponding annotated programs, which illustrate the solving process of the given problems. Compared with another publicly available dataset GeoS, GeoQA is 25 times larger, in which the program annotations can provide a practical testbed for future research on explicit and explainable numerical reasoning. Moreover, we introduce a Neural Geometric Solver (NGS) to address geometric problems by comprehensively parsing multimodal information and generating interpretable programs. We further add multiple self-supervised auxiliary tasks on NGS to enhance cross-modal semantic representation. Extensive experiments on GeoQA validate the effectiveness of our proposed NGS and auxiliary tasks. However, the results are still significantly lower than human performance, which leaves large room for future research. Our benchmark and code are released at https://github.com/chenjudge/GeoQA.

First Page

513

Last Page

523

DOI

10.18653/v1/2021.findings-acl.46

Publication Date

1-1-2021

Keywords

Annotated program; Geometric problems; Hand-craft rules; Math problem solving; Multi-modal; Numerical reasoning; Program annotation; Question Answering; Small scale; Textual description

Comments

OA deposit conditions: none described

OA version available on ACL Anthology

Link to Full Text

Share

COinS