LaTeX2Solver: a Hierarchical Semantic Parsing of LaTeX Document into Code for an Assistive Optimization Modeling Application

We demonstrate an interactive system to help operations research (OR) practitioners convert the mathematical formulation of optimization problems from LaTeX document format into the solver modeling language. In practice, a manual translation is cumbersome and timeconsuming. Moreover, it requires an in-depth understanding of the problem description and a technical expertise to produce the modeling code. Thus, our proposed system LATEX-SOLVER helps partially automate this conversion and help the users build optimization models more efficiently. In this paper, we describe its interface and the components of the hierarchical parsing system. A video demo walkthrough is available online. 1