{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/layoutmask-enhance-text-layout-interaction-in","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","arxiv_id":"2305.18721","date":"2023-05-30","proceeding":null,"authors":["Yi Tu","Ya Guo","Huan Chen","Jinyang Tang"],"abstract":"Visually-rich Document Understanding (VrDU) has attracted much research attention over the past years. Pre-trained models on a large number of document images with transformer-based backbones have led to significant performance gains in this field. The major challenge is how to fusion the different modalities (text, layout, and image) of the documents in a unified model with different pre-training tasks. This paper focuses on improving text-layout interactions and proposes a novel multi-modal pre-training model, LayoutMask. LayoutMask uses local 1D position, instead of global 1D position, as layout input and has two pre-training objectives: (1) Masked Language Modeling: predicting masked tokens with two novel masking strategies; (2) Masked Position Modeling: predicting masked 2D positions to improve layout representation learning. LayoutMask can enhance the interactions between text and layout modalities in a unified model and produce adaptive and robust multi-modal representations for downstream tasks. Experimental results show that our proposed method can achieve state-of-the-art results on a wide variety of VrDU problems, including form understanding, receipt understanding, and document image classification.","url_abs":"https://arxiv.org/abs/2305.18721v2","url_pdf":"https://arxiv.org/pdf/2305.18721v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"document-image-classification","task_name":"Document Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"key-information-extraction","task_name":"Key Information Extraction"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":null,"task_name":"Position"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-entity-labeling","task_name":"Semantic entity labeling"},{"task_slug":"document-understanding","task_name":"document understanding"},{"task_slug":"document-image-classification","task_name":"document-image-classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/key-information-extraction-on-cord","task":"Key Information Extraction","dataset":"CORD","model":"LayoutMask (large)","rank_in_archive_order":4,"of":9,"metrics":{"F1":"97.19"},"uses_additional_data":false},{"leaderboard":"/sota/key-information-extraction-on-cord","task":"Key Information Extraction","dataset":"CORD","model":"LayoutMask (base)","rank_in_archive_order":5,"of":9,"metrics":{"F1":"96.99"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-cord-r","task":"Named Entity Recognition (NER)","dataset":"CORD-r","model":"LayoutMask","rank_in_archive_order":4,"of":4,"metrics":{"F1":"81.84"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-ner-on-funsd-r","task":"Named Entity Recognition (NER)","dataset":"FUNSD-r","model":"LayoutMask","rank_in_archive_order":4,"of":4,"metrics":{"F1":"77.10"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-entity-labeling-on-funsd","task":"Semantic entity labeling","dataset":"FUNSD","model":"LayoutMask (large)","rank_in_archive_order":1,"of":15,"metrics":{"F1":"93.20"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-entity-labeling-on-funsd","task":"Semantic entity labeling","dataset":"FUNSD","model":"LayoutMask (base)","rank_in_archive_order":3,"of":15,"metrics":{"F1":"92.91"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.18721","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}