Mathematical Formula
Mathematical formula research centers on efficiently representing, recognizing, and generating mathematical expressions, primarily focusing on improving accuracy and speed. Current efforts involve developing novel neural network architectures, such as hierarchical and convolutional models, along with improved evaluation metrics that address the inherent ambiguity in formula representation. These advancements are crucial for applications ranging from automated document processing and spreadsheet formula generation to accelerating scientific discovery and enhancing the accessibility of mathematical information.
Papers
NL2Formula: Generating Spreadsheet Formulas from Natural Language Queries
Wei Zhao, Zhitao Hou, Siyuan Wu, Yan Gao, Haoyu Dong, Yao Wan, Hongyu Zhang, Yulei Sui, Haidong Zhang
FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning
Xiao Li, Bolin Zhu, Sichen Liu, Yin Zhu, Yiwei Liu, Gong Cheng