From Algebraic Word Problem to Program: A Formalized Approach
This work addresses the specific problem of automating formal program generation from word problems for educational or computational linguistics applications, but it appears incremental as it builds on existing categorization methods.
The paper tackles the problem of converting grade school algebraic word problems into formal programs using a pipeline that breaks problems into sentence fragments and reduces them to functions based on verb categories and dependency parsing. The result is a working implementation available on GitHub.
In this paper, we propose a pipeline to convert grade school level algebraic word problem into program of a formal languageA-IMP. Using natural language processing tools, we break the problem into sentence fragments which can then be reduced to functions. The functions are categorized by the head verb of the sentence and its structure, as defined by (Hosseini et al., 2014). We define the function signature and extract its arguments from the text using dependency parsing. We have a working implementation of the entire pipeline which can be found on our github repository.