Highlighting Named Entities in Input for Auto-Formulation of Optimization Problems

TL;DR

This paper introduces a machine learning approach that highlights named entities in textual descriptions to automatically convert linear programming problems into mathematical formulations, significantly improving accuracy.

Contribution

The paper proposes a novel method that emphasizes named entities in input text to enhance automatic problem formulation in operations research.

Findings

Achieved highest accuracy in NL4Opt Competition

Secured first place in the generation track

Demonstrated effectiveness of entity highlighting in problem formulation

Abstract

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.