A Bottom-Up DAG Structure Extraction Model for Math Word Problems

By Yixuan Cao, Feng Hong, Hongwei Li, Ping Luo. 2021

58 citations recorded by the source corpus.

Research on automatically solving mathematical word problems (MWP) has a long history. Most recent works adopt Seq2Seq approach to predict the result equations as a sequence of quantities and operators. Although result equations can be written as a sequence, it is essentially a structure. More precisely, it is a Direct Acyclic Graph (DAG) whose leaf nodes are the quantities, and internal and root nodes are arithmetic or comparison operators. In this paper, we propose a novel Seq2DAG approach to extract the equation set directly as a DAG structure. It is extracted in a bottom-up fashion by aggregating quantities and sub-expressions layer by layer iteratively. The advantages of our approach approach are three-fold: it is intrinsically suitable to solve multivariate problems, it always outputs valid structure, and its computation satisfies commutative law for +, x and =. Experimental results on Math23K and DRAW1K demonstrate that our model outperforms state-of-the-art deep learning methods. We also conduct detailed analysis on the results to show the strengths and limitations of our approach.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Wei Dang Lu
  2. Zhanming Jie
  3. Jierui Li
  4. Bryan Perozzi
  5. Chengqi Zhang
  6. William L. Hamilton

In Information Systems

  1. Wei Dang Lu
  2. Zhanming Jie
  3. Jierui Li

In Natural Language Processing

  1. Wei Dang Lu
  2. Zhanming Jie
  3. Jierui Li

Citations in the corpus