A persistent challenge to table question answering (TableQA) by generating
executable programs has been adapting to varied table structures, typically
requiring domain-specific logical forms. In response, this paper introduces a
unified TableQA framework that: (1) provides a unified representation for
structured tables as multi-index Pandas data frames, (2) uses Python as a
powerful querying language, and (3) uses few-shot prompting to translate NL
questions into Python programs, which are executable on Pandas data frames.
Furthermore, to answer complex relational questions with extended program
functionality and external knowledge, our framework allows customized APIs that
Python programs can call. We experiment with four TableQA datasets that involve
tables of different structures -- relational, multi-table, and hierarchical
matrix shapes -- and achieve prominent improvements over past state-of-the-art
systems. In ablation studies, we (1) show benefits from our multi-index
representation and APIs over baselines that use only an LLM, and (2)
demonstrate that our approach is modular and can incorporate additional APIs.

通过生成可执行程序的方式来回答表格问题（TableQA）一直面临的挑战是适应各种表格结构，通常需要特定领域的逻辑形式。为此，本文引入了一个统一的 TableQA 框架，该框架：（1）以多索引 Pandas 数据帧的形式提供结构化表格的统一表示；（2）使用 Python 作为强大的查询语言；（3）使用少样本提示将自然语言问题转化为可在 Pandas 数据帧上执行的 Python 程序。此外，为了回答复杂的关系性问题并具备扩展程序功能和外部知识，我们的框架允许自定义的 API，供 Python 程序调用。我们在涉及不同结构的四个 TableQA 数据集上进行了实验 —— 关系型、多表格和分层矩阵形式 —— 并在过去最先进系统的基础上取得了显著的改进。在消融研究中，我们表明相比只使用 LLM 的基线方法，我们的多索引表示和 API 可以带来好处；同时，我们还证明了我们的方法是模块化的，可以整合其他的 API。