rootsautomation/FinQA

FinQA是一个完整的重打包版本，基于FinQA数据集（Chen等人，EMNLP 2021），用于金融表格的数值推理。该数据集包含来自S&P 500公司（1999年至2019年）收益报告的问题，数据源自FinTabNet数据集。每个示例将一个金融表格及周围文本与一个问题、一个人类可读的答案以及一个结构化的推理程序配对，该程序指定了推导答案所需的算术操作。FinQA is a complete repackaged version based on the original FinQA dataset (Chen et al., EMNLP 2021), tailored for numerical reasoning over financial tables. This dataset includes questions extracted from the earnings reports of S&P 500 companies spanning 1999 to 2019, with all data sourced from the FinTabNet dataset. Each example pairs a financial table and its surrounding contextual text with a question, a human-readable answer, and a structured reasoning program that specifies the arithmetic operations required to derive the final answer.