Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

1-2019

Abstract

The design of automatic solvers to arithmetic math word problems has attracted considerable attention in recent years and a large number of datasets and methods have been published. Among them, Math23K is the largest data corpus that is very helpful to evaluate the generality and robustness of a proposed solution. The best performer in Math23K is a seq2seq model based on LSTM to generate the math expression. However, the model suffers from performance degradation in large space of target expressions. In this paper, we propose a template-based solution based on recursive neural network for math expression construction. More specifically, we first apply a seq2seq model to predict a tree-structure template, with inferred numbers as leaf nodes and unknown operators as inner nodes. Then, we design a recursive neural network to encode the quantity with Bi-LSTM and self attention, and infer the unknown operator nodes in a bottom-up manner. The experimental results clearly establish the superiority of our new framework as we improve the accuracy by a wide margin in two of the largest datasets, i.e., from 58.1% to 66.9% in Math23K and from 62.8% to 66.8% in MAWPS.

Discipline

Artificial Intelligence and Robotics | Numerical Analysis and Scientific Computing

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 33rd 2019 AAAI Conference on Artificial Intelligence: Honolulu, January 27 - February 1

Volume

33

First Page

7144

Last Page

7151

ISBN

9781577358091

Identifier

10.1609/aaai.v33i01.33017144

Publisher

AAAI Press

City or Country

Palo Alto, CA

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/10.1609/aaai.v33i01.33017144

Download

Share

COinS