Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2019

Abstract

Several deep learning models have been proposed for solving math word problems (MWPs) automatically. Although these models have the ability to capture features without manual efforts, their approaches to capturing features are not specifically designed for MWPs. To utilize the merits of deep learning models with simultaneous consideration of MWPs’ specific features, we propose a group attention mechanism to extract global features, quantity-related features, quantity-pair features and question-related features in MWPs respectively. The experimental results show that the proposed approach performs significantly better than previous state-of-the-art methods, and boost performance from 66.9% to 69.5% on Math23K with training-test split, from 65.8% to 66.9% on Math23K with 5-fold cross-validation and from 69.2% to 76.1% on MAWPS.

Keywords

Attention mechanisms, Cross validation, Global feature, Learning models, State-of-the-art methods, Word problem

Discipline

Artificial Intelligence and Robotics | Numerical Analysis and Scientific Computing

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019): Florence, July 28 - August 2

First Page

6162

Last Page

6167

ISBN

9781950737482

Identifier

10.18653/v1/P19-1619

Publisher

Association for Computational Linguistics

City or Country

Florence

Copyright Owner and License

Publisher

Creative Commons License

Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.

Additional URL

https://doi.org/10.18653/v1/P19-1619

Download

Share

COinS