Generating Math Word Problems from Equations with Topic Controlling and Commonsense Enforcement

TL;DR

This paper introduces a novel neural model for generating math word problems from equations, incorporating topic control, background knowledge, and a VAE-enhanced equation encoder, achieving superior accuracy and richness.

Contribution

The paper presents a new equation-to-problem text generation model with topic control, commonsense enforcement via background knowledge, and a VAE-based equation encoder, advancing the field.

Findings

Outperforms baseline models in accuracy.

Produces more diverse and rich problem texts.

Effective integration of background knowledge improves quality.

Abstract

Recent years have seen significant advancement in text generation tasks with the help of neural language models. However, there exists a challenging task: generating math problem text based on mathematical equations, which has made little progress so far. In this paper, we present a novel equation-to-problem text generation model. In our model, 1) we propose a flexible scheme to effectively encode math equations, we then enhance the equation encoder by a Varitional Autoen-coder (VAE) 2) given a math equation, we perform topic selection, followed by which a dynamic topic memory mechanism is introduced to restrict the topic distribution of the generator 3) to avoid commonsense violation in traditional generation model, we pretrain word embedding with background knowledge graph (KG), and we link decoded words to related words in KG, targeted at injecting background knowledge into our model. We evaluate our model through both automatic metrices and human evaluation, experiments demonstrate our model outperforms baseline and previous models in both accuracy and richness of generated problem text.