LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receipts
This work addresses the problem of limited multimodal resources for Vietnamese document analysis, specifically for receipts, which is incremental as it adapts existing VQA methods to a new language and domain.
The paper tackles the lack of Vietnamese document VQA datasets by introducing ReceiptVQA, a dataset with over 9,000 receipt images and 60,000 question-answer pairs, and proposes LiGT, a layout-aware transformer architecture that achieves competitive results on this dataset.
Document Visual Question Answering (Document VQA) challenges multimodal systems to holistically handle textual, layout, and visual modalities to provide appropriate answers. Document VQA has gained popularity in recent years due to the increasing amount of documents and the high demand for digitization. Nonetheless, most of document VQA datasets are developed in high-resource languages such as English. In this paper, we present ReceiptVQA (\textbf{Receipt} \textbf{V}isual \textbf{Q}uestion \textbf{A}nswering), the initial large-scale document VQA dataset in Vietnamese dedicated to receipts, a document kind with high commercial potentials. The dataset encompasses \textbf{9,000+} receipt images and \textbf{60,000+} manually annotated question-answer pairs. In addition to our study, we introduce LiGT (\textbf{L}ayout-\textbf{i}nfused \textbf{G}enerative \textbf{T}ransformer), a layout-aware encoder-decoder architecture designed to leverage embedding layers of language models to operate layout embeddings, minimizing the use of additional neural modules. Experiments on ReceiptVQA show that our architecture yielded promising performance, achieving competitive results compared with outstanding baselines. Furthermore, throughout analyzing experimental results, we found evident patterns that employing encoder-only model architectures has considerable disadvantages in comparison to architectures that can generate answers. We also observed that it is necessary to combine multiple modalities to tackle our dataset, despite the critical role of semantic understanding from language models. We hope that our work will encourage and facilitate future development in Vietnamese document VQA, contributing to a diverse multimodal research community in the Vietnamese language.