This website requires JavaScript.

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

Neeraj GangwarNickvash Kani
Dec 2022
摘要
Operations research deals with modeling and solving real-world problems asmathematical optimization problems. While solving mathematical systems isaccomplished by analytical software, formulating a problem as a set ofmathematical operations has been typically done manually by domain experts.However, recent machine learning models have shown promise in convertingtextual problem descriptions to corresponding mathematical formulations. Inthis paper, we present an approach that converts linear programming wordproblems into meaning representations that are structured and can be used byoptimization solvers. Our approach uses the named entity-based enrichment toaugment the input and achieves state-of-the-art accuracy, winning the secondtask of the NL4Opt competition (https://nl4opt.github.io).
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答