LAMBERT: Layout-Aware (Language) Modeling for information extraction
This addresses the challenge of information extraction from documents with complex layouts for applications like OCR and data processing, representing an incremental improvement over existing methods.
The paper tackles the problem of understanding documents where layout influences semantics by introducing a layout-aware language model that integrates token bounding box coordinates into a Transformer encoder, achieving superior performance on visually rich document datasets and improving SOTA F1-score on SROIE from 97.81 to 98.17.
We introduce a simple new approach to the problem of understanding documents where non-trivial layout influences the local semantics. To this end, we modify the Transformer encoder architecture in a way that allows it to use layout features obtained from an OCR system, without the need to re-learn language semantics from scratch. We only augment the input of the model with the coordinates of token bounding boxes, avoiding, in this way, the use of raw images. This leads to a layout-aware language model which can then be fine-tuned on downstream tasks. The model is evaluated on an end-to-end information extraction task using four publicly available datasets: Kleister NDA, Kleister Charity, SROIE and CORD. We show that our model achieves superior performance on datasets consisting of visually rich documents, while also outperforming the baseline RoBERTa on documents with flat layout (NDA \(F_{1}\) increase from 78.50 to 80.42). Our solution ranked first on the public leaderboard for the Key Information Extraction from the SROIE dataset, improving the SOTA \(F_{1}\)-score from 97.81 to 98.17.