TexTAR : Textual Attribute Recognition in Multi-domain and Multi-lingual Document Images
This addresses document analysis for applications like legal records and textbooks, but is incremental as it builds on existing Transformer methods for a specific task.
The paper tackles the problem of recognizing textual attributes like bold and italic in noisy, multilingual document images by introducing TexTAR, a multi-task Transformer with a novel data selection pipeline and 2D RoPE mechanism, which outperforms existing methods in evaluations.
Recognizing textual attributes such as bold, italic, underline and strikeout is essential for understanding text semantics, structure, and visual presentation. These attributes highlight key information, making them crucial for document analysis. Existing methods struggle with computational efficiency or adaptability in noisy, multilingual settings. To address this, we introduce TexTAR, a multi-task, context-aware Transformer for Textual Attribute Recognition (TAR). Our novel data selection pipeline enhances context awareness, and our architecture employs a 2D RoPE (Rotary Positional Embedding)-style mechanism to incorporate input context for more accurate attribute predictions. We also introduce MMTAD, a diverse, multilingual, multi-domain dataset annotated with text attributes across real-world documents such as legal records, notices, and textbooks. Extensive evaluations show TexTAR outperforms existing methods, demonstrating that contextual awareness contributes to state-of-the-art TAR performance.