TabIQA: Table Questions Answering on Business Document Images

TL;DR

TabIQA is a novel deep learning pipeline that effectively extracts and interprets complex tabular data from business document images to answer diverse questions, demonstrating promising results on a challenging dataset.

Contribution

The paper introduces TabIQA, a new pipeline combining advanced deep learning techniques for extracting and reasoning over table data in business document images.

Findings

Effective extraction of table content and structure from images

Successful answering of complex questions involving numerical and text data

Promising performance on VQAonBD 2023 dataset

Abstract

Table answering questions from business documents has many challenges that require understanding tabular structures, cross-document referencing, and additional numeric computations beyond simple search queries. This paper introduces a novel pipeline, named TabIQA, to answer questions about business document images. TabIQA combines state-of-the-art deep learning techniques 1) to extract table content and structural information from images and 2) to answer various questions related to numerical data, text-based information, and complex queries from structured tables. The evaluation results on VQAonBD 2023 dataset demonstrate the effectiveness of TabIQA in achieving promising performance in answering table-related questions. The TabIQA repository is available at https://github.com/phucty/itabqa.