将大表格分块处理，用模型逐块筛选相关单元格，拼成小表格提升问答准确率。
Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering
- 分块迭代筛选：把大表拆成小窗口，逐块用语言模型选相关单元格。
- 多分辨率捕捉依赖：兼顾行间列间关系，避免长文本导致信息丢失。
- 适合复杂表格问答：特别适合需要跨行跨列表达的复杂查询场景。
将语言模型（LMs）应用于表格面临挑战，因二维表格与一维文本结构差异大。线性化表格常受限于自注意力机制的最大标记长度，难以全面理解大型表格中的上下文。为此，我们提出PieTa（Piece of Table），一种基于子表的问答框架。PieTa通过迭代过程将表格划分为更小的窗口，利用语言模型在每个窗口内选择相关单元格，并将这些单元格合并为子表。该多分辨率方法能有效捕捉跨行跨列依赖，同时避免长上下文输入带来的限制。作为简单的迭代子表合并算法，PieTa在性能上优于以往基于子表的问答方法。
原文摘要 · Abstract (English)
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 subtable-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 subtable. 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 subtable union algorithm, PieTa demonstrates improved performance over previous subtable-based QA approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。