Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering

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 linearized tables are applied to LMs, the maximum token length constraints imposed by self-attention mechanisms 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 a multiresolution iterative process: dividing tables into smaller windows, using LMs to select relevant cells within each window, and merging these cells to form a subtable. This approach enables the model to capture dependencies across multiple rows and columns while mitigating the limitations of long context inputs. Instantiated as a simple iterative subtable union algorithm, PieTa achieves significantly improved performance over previous subtable-based QA approaches.