Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations
This work addresses the need for diverse and realistic MWP generation in educational assessment, though it appears incremental as it builds on existing neural methods for text generation.
The paper tackles the problem of generating mathematical word problems (MWPs) that maintain correct mathematical operations and topic relevance by developing an end-to-end neural model that uses commonsense knowledge graphs and equations. The model outperforms state-of-the-art models on both automatic metrics like BLEU-4 and human evaluation metrics for equation and topic relevance.
There is an increasing interest in the use of mathematical word problem (MWP) generation in educational assessment. Different from standard natural question generation, MWP generation needs to maintain the underlying mathematical operations between quantities and variables, while at the same time ensuring the relevance between the output and the given topic. To address above problem, we develop an end-to-end neural model to generate diverse MWPs in real-world scenarios from commonsense knowledge graph and equations. The proposed model (1) learns both representations from edge-enhanced Levi graphs of symbolic equations and commonsense knowledge; (2) automatically fuses equation and commonsense knowledge information via a self-planning module when generating the MWPs. Experiments on an educational gold-standard set and a large-scale generated MWP set show that our approach is superior on the MWP generation task, and it outperforms the SOTA models in terms of both automatic evaluation metrics, i.e., BLEU-4, ROUGE-L, Self-BLEU, and human evaluation metrics, i.e., equation relevance, topic relevance, and language coherence. To encourage reproducible results, we make our code and MWP dataset public available at \url{https://github.com/tal-ai/MaKE_EMNLP2021}.