Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions
Computation and Language
2022-10-13 v2 Artificial Intelligence
Abstract
We describe an augmented intelligence system for simplifying and enhancing the modeling experience for operations research. Using this system, the user receives a suggested formulation of an optimization problem based on its description. To facilitate this process, we build an intuitive user interface system that enables the users to validate and edit the suggestions. We investigate controlled generation techniques to obtain an automatic suggestion of formulation. Then, we evaluate their effectiveness with a newly created dataset of linear programming problems drawn from various application domains.
Cite
@article{arxiv.2209.15565,
title = {Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions},
author = {Rindranirina Ramamonjison and Haley Li and Timothy T. Yu and Shiqi He and Vishnu Rengan and Amin Banitalebi-Dehkordi and Zirui Zhou and Yong Zhang},
journal= {arXiv preprint arXiv:2209.15565},
year = {2022}
}
Comments
Accepted for presentation at the EMNLP 2022 Conference (industry track)