Generating Math Word Problems from Equations with Topic Controlling and Commonsense Enforcement
This work is significant for students and educators who need to generate diverse and accurate math word problems from equations, an area where existing models struggle with accuracy and commonsense violations.
This paper addresses the challenge of generating math word problems from equations, a task that has seen limited progress. The authors propose a novel model that outperforms baseline and previous models in both the accuracy and richness of generated problem text.
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.