arXiv:2109.07323cs.IR
FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
Tables store rich numerical data, but numerical reasoning over tables is still a challenge. In this paper, we find that the spreadsheet formula, which performs calculations on numerical values in tables, is naturally a strong supervision of numerical reasoning. More importantly, large amounts of spreadsheets with expert-made formulae are available on the web and can be obtained easily. FORTAP is the first method for numerical-reasoning-aware table pretraining by leveraging large corpus of spreadsheet formulae. We design two formula pretraining tasks to explicitly guide FORTAP to learn numerical reference and calculation in semi-structured tables. FORTAP achieves state-of-the-art results on two representative downstream tasks, cell type classification and formula prediction, showing great potential of numerical-reasoning-aware pretraining.
There's also a book on the subject: https://en.wikipedia.org/wiki/The_History_of_Mathematical_Ta... Interesting aside: AI models trained on spreadsheets need "good tables" such as column names, headers, etc. to understand context. Like Fortap: https://arxiv.org/abs/2109.07323
antidnanView on HNParent context