{"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/dublin-document-understanding-by-language","title":"DUBLIN -- Document Understanding By Language-Image Network","arxiv_id":"2305.14218","date":"2023-05-23","proceeding":null,"authors":["Kriti Aggarwal","Aditi Khandelwal","Kumar Tanmay","Owais Mohammed Khan","Qiang Liu","Monojit Choudhury","Hardik Hansrajbhai Chauhan","Subhojit Som","Vishrav Chaudhary","Saurabh Tiwary"],"abstract":"Visual document understanding is a complex task that involves analyzing both the text and the visual elements in document images. Existing models often rely on manual feature engineering or domain-specific pipelines, which limit their generalization ability across different document types and languages. In this paper, we propose DUBLIN, which is pretrained on web pages using three novel objectives: Masked Document Text Generation Task, Bounding Box Task, and Rendered Question Answering Task, that leverage both the spatial and semantic information in the document images. Our model achieves competitive or state-of-the-art results on several benchmarks, such as Web-Based Structural Reading Comprehension, Document Visual Question Answering, Key Information Extraction, Diagram Understanding, and Table Question Answering. In particular, we show that DUBLIN is the first pixel-based model to achieve an EM of 77.75 and F1 of 84.25 on the WebSRC dataset. We also show that our model outperforms the current pixel-based SOTA models on DocVQA, InfographicsVQA, OCR-VQA and AI2D datasets by 4.6%, 6.5%, 2.6% and 21%, respectively. We also achieve competitive performance on RVL-CDIP document classification. Moreover, we create new baselines for text-based datasets by rendering them as document images to promote research in this direction.","url_abs":"https://arxiv.org/abs/2305.14218v4","url_pdf":"https://arxiv.org/pdf/2305.14218v4.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-classification","task_name":"Document Classification"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"key-information-extraction","task_name":"Key Information Extraction"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-vqa-on-ai2d","task":"Visual Question Answering (VQA)","dataset":"AI2D","model":"DUBLIN","rank_in_archive_order":4,"of":4,"metrics":{"EM":"51.11"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-deepform","task":"Visual Question Answering (VQA)","dataset":"DeepForm","model":"DUBLIN","rank_in_archive_order":1,"of":1,"metrics":{"F1":"62.23"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"DUBLIN (variable resolution)","rank_in_archive_order":22,"of":33,"metrics":{"ANLS":"0.803"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"DUBLIN","rank_in_archive_order":24,"of":33,"metrics":{"ANLS":"0.782"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-vqa-on","task":"Visual Question Answering (VQA)","dataset":"InfographicVQA","model":"DUBLIN (variable resolution)","rank_in_archive_order":17,"of":21,"metrics":{"ANLS":"42.6"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-vqa-on","task":"Visual Question Answering (VQA)","dataset":"InfographicVQA","model":"DUBLIN","rank_in_archive_order":21,"of":21,"metrics":{"ANLS":"36.82"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-vqa-on-websrc","task":"Visual Question Answering (VQA)","dataset":"WebSRC","model":"DUBLIN","rank_in_archive_order":1,"of":1,"metrics":{"EM":"77.75"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.14218","atlas_url":"https://app.syntology.ai/?focus=2305.14218","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":"2305.14218"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2305.14218\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2305.14218"},"call":"get_concepts_for_paper(arxiv_id=\"2305.14218\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5c238cf6c2c583633a5eff53cdb11834048dbd447b1952458df0f4deb7e1bc19","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}