Highlighting Named Entities in Input for Auto-Formulation of Optimization Problems
This addresses the challenge of manual problem formulation in operations research, offering an incremental improvement for domain experts by automating part of the process.
The paper tackles the problem of automatically converting linear programming word problems into mathematical formulations by highlighting named entities in the input, achieving first place in the NL4Opt Competition generation track with the highest accuracy among submissions.
Operations research deals with modeling and solving real-world problems as mathematical optimization problems. While solving mathematical systems is accomplished by analytical software, formulating a problem as a set of mathematical operations has been typically done manually by domain experts. Recent machine learning methods have shown promise in converting textual problem descriptions to corresponding mathematical formulations. This paper presents an approach that converts linear programming word problems into mathematical formulations. We leverage the named entities in the input and augment the input to highlight these entities. Our approach achieves the highest accuracy among all submissions to the NL4Opt Competition, securing first place in the generation track.