Spatial Information Integration in Small Language Models for Document Layout Generation and Classification
This work addresses a data shortage issue for researchers and practitioners working with semi-structured documents like receipts and balance sheets, though it is incremental as it builds on existing layout generation methods.
The authors tackled the problem of limited public datasets for semi-structured document layout understanding by proposing a method to generate synthetic layout information, which outperformed LayoutTransformer in layout generation and showed that bounding box information can improve text classification in some scenarios.
Document layout understanding is a field of study that analyzes the spatial arrangement of information in a document hoping to understand its structure and layout. Models such as LayoutLM (and its subsequent iterations) can understand semi-structured documents with SotA results; however, the lack of open semi-structured data is a limitation in itself. While semi-structured data is common in everyday life (balance sheets, purchase orders, receipts), there is a lack of public datasets for training machine learning models for this type of document. In this investigation we propose a method to generate new, synthetic, layout information that can help overcoming this data shortage. According to our results, the proposed method performs better than LayoutTransformer, another popular layout generation method. We also show that, in some scenarios, text classification can improve when supported by bounding box information.