LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
This work addresses the problem of language dependency in document understanding for researchers and practitioners, offering a practical solution that is incremental but broadens applicability.
The paper tackles the limitation of existing structured document understanding models that are restricted to specific languages by proposing LiLT, a language-independent layout transformer that achieves competitive or superior performance across eight languages on various benchmarks.
Structured document understanding has attracted considerable attention and made significant progress recently, owing to its crucial role in intelligent document processing. However, most existing related models can only deal with the document data of specific language(s) (typically English) included in the pre-training collection, which is extremely limited. To address this issue, we propose a simple yet effective Language-independent Layout Transformer (LiLT) for structured document understanding. LiLT can be pre-trained on the structured documents of a single language and then directly fine-tuned on other languages with the corresponding off-the-shelf monolingual/multilingual pre-trained textual models. Experimental results on eight languages have shown that LiLT can achieve competitive or even superior performance on diverse widely-used downstream benchmarks, which enables language-independent benefit from the pre-training of document layout structure. Code and model are publicly available at https://github.com/jpWang/LiLT.