Applying language models (LMs) to tables is challenging due to the inherent structural differences between two-dimensional tables and one-dimensional text for which the LMs were originally designed. Furthermore, when applying linearized tables to LMs, the maximum token lengths often imposed in self-attention calculations make it difficult to comprehensively understand the context spread across large tables. To address these challenges, we present PieTa (Piece of Table), a new framework for sub-table-based question answering (QA). PieTa operates through an iterative process of dividing tables into smaller windows, using LMs to select relevant cells within each window, and merging these cells into a sub-table. This multi-resolution approach captures dependencies across multiple rows and columns while avoiding the limitations caused by long context inputs. Instantiated as a simple iterative sub-table union algorithm, PieTa demonstrates improved performance over previous sub-table-based QA approaches.

翻译：将语言模型应用于表格具有挑战性，因为二维表格与语言模型最初为之设计的一维文本之间存在固有的结构差异。此外，当将线性化表格输入语言模型时，自注意力计算中通常施加的最大令牌长度限制，使得模型难以全面理解分布在大型表格中的上下文信息。为应对这些挑战，我们提出了PieTa（表格片段），一种基于子表进行问答的新框架。PieTa通过迭代过程运行：将表格划分为更小的窗口，使用语言模型在每个窗口中选择相关单元格，并将这些单元格合并成一个子表。这种多分辨率方法能够捕捉跨多行多列的依赖关系，同时避免了长上下文输入带来的限制。PieTa被实例化为一种简单的迭代子表合并算法，其性能优于以往基于子表的问答方法。