NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions

Rindranirina Ramamonjison, Timothy Yu, Raymond Li, Haley Li, Giuseppe Carenini, Bissan Ghaddar, Shiqi He, Mahdi Mostajabdaveh, Amin Banitalebi-Dehkordi, Zirui Zhou, Yong Zhang
Proceedings of the NeurIPS 2022 Competitions Track, PMLR 220:189-203, 2022.

Abstract

The Natural Language for Optimization (NL4Opt) Competition was created to investigate methods of extracting the meaning and formulation of an optimization problem based on its text description. Specifically, the goal of the competition is to increase the accessibility and usability of optimization solvers by allowing non-experts to interface with them using natural language. We separate this challenging goal into two sub-tasks: (1) recognize and label the semantic entities that correspond to the components of the optimization problem; (2) generate a meaning representation (i.e. a logical form) of the problem from its detected problem entities. The first task aims to reduce ambiguity by detecting and tagging the entities of the optimization problems. The second task creates an intermediate representation of the linear programming (LP) problem that is converted into a format that can be used by commercial solvers. In this report, we present the LP word problem dataset and shared tasks for the NeurIPS 2022 competition. Furthermore, we present the winning solutions. Through this competition, we hope to bring interest towards the development of novel machine learning applications and datasets for optimization modeling.

Cite this Paper

BibTeX
@InProceedings{pmlr-v220-ramamonjison23a, title = {NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions}, author = {Ramamonjison, Rindranirina and Yu, Timothy and Li, Raymond and Li, Haley and Carenini, Giuseppe and Ghaddar, Bissan and He, Shiqi and Mostajabdaveh, Mahdi and Banitalebi-Dehkordi, Amin and Zhou, Zirui and Zhang, Yong}, booktitle = {Proceedings of the NeurIPS 2022 Competitions Track}, pages = {189--203}, year = {2022}, editor = {Ciccone, Marco and Stolovitzky, Gustavo and Albrecht, Jacob}, volume = {220}, series = {Proceedings of Machine Learning Research}, month = {28 Nov--09 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v220/ramamonjison23a/ramamonjison23a.pdf}, url = {https://proceedings.mlr.press/v220/ramamonjison23a.html}, abstract = {The Natural Language for Optimization (NL4Opt) Competition was created to investigate methods of extracting the meaning and formulation of an optimization problem based on its text description. Specifically, the goal of the competition is to increase the accessibility and usability of optimization solvers by allowing non-experts to interface with them using natural language. We separate this challenging goal into two sub-tasks: (1) recognize and label the semantic entities that correspond to the components of the optimization problem; (2) generate a meaning representation (i.e. a logical form) of the problem from its detected problem entities. The first task aims to reduce ambiguity by detecting and tagging the entities of the optimization problems. The second task creates an intermediate representation of the linear programming (LP) problem that is converted into a format that can be used by commercial solvers. In this report, we present the LP word problem dataset and shared tasks for the NeurIPS 2022 competition. Furthermore, we present the winning solutions. Through this competition, we hope to bring interest towards the development of novel machine learning applications and datasets for optimization modeling.} }
Endnote
%0 Conference Paper %T NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions %A Rindranirina Ramamonjison %A Timothy Yu %A Raymond Li %A Haley Li %A Giuseppe Carenini %A Bissan Ghaddar %A Shiqi He %A Mahdi Mostajabdaveh %A Amin Banitalebi-Dehkordi %A Zirui Zhou %A Yong Zhang %B Proceedings of the NeurIPS 2022 Competitions Track %C Proceedings of Machine Learning Research %D 2022 %E Marco Ciccone %E Gustavo Stolovitzky %E Jacob Albrecht %F pmlr-v220-ramamonjison23a %I PMLR %P 189--203 %U https://proceedings.mlr.press/v220/ramamonjison23a.html %V 220 %X The Natural Language for Optimization (NL4Opt) Competition was created to investigate methods of extracting the meaning and formulation of an optimization problem based on its text description. Specifically, the goal of the competition is to increase the accessibility and usability of optimization solvers by allowing non-experts to interface with them using natural language. We separate this challenging goal into two sub-tasks: (1) recognize and label the semantic entities that correspond to the components of the optimization problem; (2) generate a meaning representation (i.e. a logical form) of the problem from its detected problem entities. The first task aims to reduce ambiguity by detecting and tagging the entities of the optimization problems. The second task creates an intermediate representation of the linear programming (LP) problem that is converted into a format that can be used by commercial solvers. In this report, we present the LP word problem dataset and shared tasks for the NeurIPS 2022 competition. Furthermore, we present the winning solutions. Through this competition, we hope to bring interest towards the development of novel machine learning applications and datasets for optimization modeling.
APA
Ramamonjison, R., Yu, T., Li, R., Li, H., Carenini, G., Ghaddar, B., He, S., Mostajabdaveh, M., Banitalebi-Dehkordi, A., Zhou, Z. & Zhang, Y.. (2022). NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions. Proceedings of the NeurIPS 2022 Competitions Track, in Proceedings of Machine Learning Research 220:189-203 Available from https://proceedings.mlr.press/v220/ramamonjison23a.html.

Related Material