| Title: |
Distilling Wikipedia mathematical knowledge into neural network models |
| Authors: |
Kim, Joanne T., Landajuela, Mikel, Petersen, Brenden K. |
| Source: |
1st Mathematical Reasoning in General Artificial Intelligence Workshop, ICLR 2021 |
| Publication Year: |
2021 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Machine Learning, Computer Science - Artificial Intelligence |
| More Details: |
Machine learning applications to symbolic mathematics are becoming increasingly popular, yet there lacks a centralized source of real-world symbolic expressions to be used as training data. In contrast, the field of natural language processing leverages resources like Wikipedia that provide enormous amounts of real-world textual data. Adopting the philosophy of "mathematics as language," we bridge this gap by introducing a pipeline for distilling mathematical expressions embedded in Wikipedia into symbolic encodings to be used in downstream machine learning tasks. We demonstrate that a $\textit{mathematical}$ $\textit{language}$ $\textit{model}$ trained on this "corpus" of expressions can be used as a prior to improve the performance of neural-guided search for the task of symbolic regression.
Comment: 6 pages, 4 figures |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2104.05930 |
| Accession Number: |
edsarx.2104.05930 |
| Database: |
arXiv |
