Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering
This work addresses the problem of handling large tables in question answering for users of language models, representing an incremental improvement over existing subtable-based approaches.
The paper tackles the challenge of applying language models to large tables by introducing PieTa, a divide-and-conquer framework that iteratively selects relevant cells to form subtables for question answering, resulting in improved performance over prior subtable-based methods.
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.