{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/geolayoutlm-geometric-pre-training-for-visual","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","arxiv_id":"2304.10759","date":"2023-04-21","proceeding":"CVPR 2023 1","authors":["Chuwei Luo","Changxu Cheng","Qi Zheng","Cong Yao"],"abstract":"Visual information extraction (VIE) plays an important role in Document Intelligence. Generally, it is divided into two tasks: semantic entity recognition (SER) and relation extraction (RE). Recently, pre-trained models for documents have achieved substantial progress in VIE, particularly in SER. However, most of the existing models learn the geometric representation in an implicit way, which has been found insufficient for the RE task since geometric information is especially crucial for RE. Moreover, we reveal another factor that limits the performance of RE lies in the objective gap between the pre-training phase and the fine-tuning phase for RE. To tackle these issues, we propose in this paper a multi-modal framework, named GeoLayoutLM, for VIE. GeoLayoutLM explicitly models the geometric relations in pre-training, which we call geometric pre-training. Geometric pre-training is achieved by three specially designed geometry-related pre-training tasks. Additionally, novel relation heads, which are pre-trained by the geometric pre-training tasks and fine-tuned for RE, are elaborately designed to enrich and enhance the feature representation. According to extensive experiments on standard VIE benchmarks, GeoLayoutLM achieves highly competitive scores in the SER task and significantly outperforms the previous state-of-the-arts for RE (\\eg, the F1 score of RE on FUNSD is boosted from 80.35\\% to 89.45\\%). The code and models are publicly available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/GeoLayoutLM","url_abs":"https://arxiv.org/abs/2304.10759v1","url_pdf":"https://arxiv.org/pdf/2304.10759v1.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":[{"paper_slug":"geolayoutlm-geometric-pre-training-for-visual","repo_url":"https://github.com/alibabaresearch/advancedliteratemachinery","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"document-ai","task_name":"Document AI"},{"task_slug":"entity-linking","task_name":"Entity Linking"},{"task_slug":"key-information-extraction","task_name":"Key Information Extraction"},{"task_slug":"key-value-pair-extraction","task_name":"Key-value Pair Extraction"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"semantic-entity-labeling","task_name":"Semantic entity labeling"},{"task_slug":"entity-extraction-2","task_name":"entity_extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/entity-linking-on-funsd","task":"Entity Linking","dataset":"FUNSD","model":"GeoLayoutLM","rank_in_archive_order":1,"of":7,"metrics":{"F1":"89.45"},"uses_additional_data":false},{"leaderboard":"/sota/key-information-extraction-on-cord","task":"Key Information Extraction","dataset":"CORD","model":"GeoLayoutLM","rank_in_archive_order":2,"of":9,"metrics":{"F1":"97.97"},"uses_additional_data":false},{"leaderboard":"/sota/key-value-pair-extraction-on-rfund-en","task":"Key-value Pair Extraction","dataset":"RFUND-EN","model":"GeoLayoutLM","rank_in_archive_order":6,"of":13,"metrics":{"key-value pair F1":"69.03"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-funsd","task":"Relation Extraction","dataset":"FUNSD","model":"GeoLayoutLM","rank_in_archive_order":2,"of":9,"metrics":{"F1":"89.45"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-funsd","task":"Relation Extraction","dataset":"FUNSD","model":"LayoutLMv3 large","rank_in_archive_order":5,"of":9,"metrics":{"F1":"80.35"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-entity-labeling-on-funsd","task":"Semantic entity labeling","dataset":"FUNSD","model":"GeoLayoutLM","rank_in_archive_order":4,"of":15,"metrics":{"F1":"92.86"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.10759","atlas_url":"https://app.syntology.ai/?focus=2304.10759","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2304.10759"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2304.10759\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2304.10759"},"call":"get_concepts_for_paper(arxiv_id=\"2304.10759\")"}],"by_repo":[{"repo":"alibabaresearch/advancedliteratemachinery","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2403.19128","2404.05225"],"harvested_for_calls":[{"arxiv_id":"2403.19128","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.19128"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.19128\")"},{"arxiv_id":"2404.05225","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.05225"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.05225\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b790e68fda712a7ee41c50b60c59f53abfb1f607f91a5e6d67cb7f47b0e92b52","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}