{"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/lights-camera-action-a-framework-to-improve","title":"Lights, Camera, Action! A Framework to Improve NLP Accuracy over OCR documents","arxiv_id":"2108.02899","date":"2021-08-06","proceeding":null,"authors":["Amit Gupte","Alexey Romanov","Sahitya Mantravadi","Dalitso Banda","Jianjie Liu","Raza Khan","Lakshmanan Ramu Meenal","Benjamin Han","Soundar Srinivasan"],"abstract":"Document digitization is essential for the digital transformation of our societies, yet a crucial step in the process, Optical Character Recognition (OCR), is still not perfect. Even commercial OCR systems can produce questionable output depending on the fidelity of the scanned documents. In this paper, we demonstrate an effective framework for mitigating OCR errors for any downstream NLP task, using Named Entity Recognition (NER) as an example. We first address the data scarcity problem for model training by constructing a document synthesis pipeline, generating realistic but degraded data with NER labels. We measure the NER accuracy drop at various degradation levels and show that a text restoration model, trained on the degraded data, significantly closes the NER accuracy gaps caused by OCR errors, including on an out-of-domain dataset. For the benefit of the community, we have made the document synthesis pipeline available as an open-source project.","url_abs":"https://arxiv.org/abs/2108.02899v1","url_pdf":"https://arxiv.org/pdf/2108.02899v1.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":"lights-camera-action-a-framework-to-improve","repo_url":"https://github.com/microsoft/genalog","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.02899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02899"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/genalog","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a0527cd400e4f6eb","entry":"blur","repo":"microsoft/genalog","repo_kind":"official","path":"genalog/degradation/effect.py","file_url":"https://github.com/microsoft/genalog/blob/HEAD/genalog/degradation/effect.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0527cd400e4f6eb"}},{"code_sha256_prefix":"b0702ab0f5b44f43","entry":"get_align_stats","repo":"microsoft/genalog","repo_kind":"official","path":"genalog/ocr/metrics.py","file_url":"https://github.com/microsoft/genalog/blob/HEAD/genalog/ocr/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0702ab0f5b44f43"}},{"code_sha256_prefix":"da1a86efdef97f86","entry":"get_editops_stats","repo":"microsoft/genalog","repo_kind":"official","path":"genalog/ocr/metrics.py","file_url":"https://github.com/microsoft/genalog/blob/HEAD/genalog/ocr/metrics.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da1a86efdef97f86"}},{"code_sha256_prefix":"81b23c26fa0201de","entry":"get_unique_words","repo":"microsoft/genalog","repo_kind":"official","path":"genalog/text/anchor.py","file_url":"https://github.com/microsoft/genalog/blob/HEAD/genalog/text/anchor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81b23c26fa0201de"}},{"code_sha256_prefix":"7f6aa68965e518c5","entry":"get_word_map","repo":"microsoft/genalog","repo_kind":"official","path":"genalog/text/anchor.py","file_url":"https://github.com/microsoft/genalog/blob/HEAD/genalog/text/anchor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f6aa68965e518c5"}},{"code_sha256_prefix":"93d0820e0475e08d","entry":"overlay","repo":"microsoft/genalog","repo_kind":"official","path":"genalog/degradation/effect.py","file_url":"https://github.com/microsoft/genalog/blob/HEAD/genalog/degradation/effect.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93d0820e0475e08d"}},{"code_sha256_prefix":"9e2d72566ebeaa20","entry":"overlay_weighted","repo":"microsoft/genalog","repo_kind":"official","path":"genalog/degradation/effect.py","file_url":"https://github.com/microsoft/genalog/blob/HEAD/genalog/degradation/effect.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e2d72566ebeaa20"}},{"code_sha256_prefix":"3927b607f2de3f3d","entry":"segment_len","repo":"microsoft/genalog","repo_kind":"official","path":"genalog/text/anchor.py","file_url":"https://github.com/microsoft/genalog/blob/HEAD/genalog/text/anchor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3927b607f2de3f3d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}