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

TL;DR

PieTa introduces a divide-and-conquer framework for table question answering that iteratively selects relevant subtables, effectively handling large tables and structural differences to improve understanding and performance.

Contribution

The paper proposes PieTa, a novel multi-resolution subtable selection method that overcomes token length limitations and captures table dependencies more effectively.

Findings

PieTa outperforms previous subtable-based QA methods.

The iterative subtable union algorithm improves context understanding.

PieTa effectively handles large and complex tables.

Abstract

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.