paper-with-me

Papers

FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining

2021-09-15 · ACL 2022 5 · Zhoujun Cheng, Haoyu Dong, Ran Jia, Pengfei Wu, Shi Han, Fan Cheng, Dongmei Zhang

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.

📄 PDF Abstract BibTeX arXiv:2109.07323

Code (1)

microsoft/TUTA_table_understanding 공식 구현 pytorch

Similar Papers 제목 키워드 기반

FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Tables store rich numerical data, but numerical reasoning over tables is still a challenge. In this paper, we find that the spreadsheet formula, a commonly used language to perform computations on numerical values in spr…

PredictionQuestion Answering

FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning

2024-02-20 · Xiao Li, Bolin Zhu, Kaiwen Shi, Sichen Liu 외

The application of formulas (e.g., physics formulas) is a fundamental ability of humans when solving numerical reasoning problems. Existing numerical reasoning datasets seldom explicitly indicate the formulas employed in…

Data AugmentationHigh School PhysicsQuestion AnsweringRetrieval+1

FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models

2024-01-19 · Ziqiang Yuan, Kaiyuan Wang, Shoutai Zhu, Ye Yuan 외

Large Language models (LLMs) usually rely on extensive training datasets. In the financial domain, creating numerical reasoning datasets that include a mix of tables and long text often involves substantial manual annota…

Dataset GenerationQuestion Answering

Fortune: Formula-Driven Reinforcement Learning for Symbolic Table Reasoning in Language Models

2025-05-29 · Lang Cao, Jingxian Xu, Hanbing Liu, Jinyu Wang 외

Tables are a fundamental structure for organizing and analyzing data, making effective table understanding a critical capability for intelligent systems. While large language models (LMs) demonstrate strong general reaso…

Question AnsweringReinforcement Learning (RL)

MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning

2026-06-10 · Abdelrahman Abdallah, AbdelRahim A. Elmadany, Sameh Al Natour, Hasan Cavusoglu 외 arxiv

Financial and tabular question answering requires more than fluent reasoning: answers must be grounded in the exact facts, formulas, units, signs, and scales that support them. A single misread cell or incorrect operatio…

Question Answering