{"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/hrdoc-dataset-and-baseline-method-toward","title":"HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures","arxiv_id":"2303.13839","date":"2023-03-24","proceeding":null,"authors":["Jiefeng Ma","Jun Du","Pengfei Hu","Zhenrong Zhang","Jianshu Zhang","Huihui Zhu","Cong Liu"],"abstract":"The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page, neglecting the reconstruction of semantic structure in multi-page documents. This paper introduces hierarchical reconstruction of document structures as a novel task suitable for NLP and CV fields. To better evaluate the system performance on the new task, we built a large-scale dataset named HRDoc, which consists of 2,500 multi-page documents with nearly 2 million semantic units. Every document in HRDoc has line-level annotations including categories and relations obtained from rule-based extractors and human annotators. Moreover, we proposed an encoder-decoder-based hierarchical document structure parsing system (DSPS) to tackle this problem. By adopting a multi-modal bidirectional encoder and a structure-aware GRU decoder with soft-mask operation, the DSPS model surpass the baseline method by a large margin. All scripts and datasets will be made publicly available at https://github.com/jfma-USTC/HRDoc.","url_abs":"https://arxiv.org/abs/2303.13839v1","url_pdf":"https://arxiv.org/pdf/2303.13839v1.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":"hrdoc-dataset-and-baseline-method-toward","repo_url":"https://github.com/jfma-ustc/hrdoc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[{"method_slug":"gru","method_name":"GRU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.13839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13839"}},"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":"deterministic:regex_extraction","url":"https://github.com/jfma-USTC/HRDoc","reach":null}],"summary":{"ran":8,"ran_draft_wrong":2,"ran_honours":2,"unverified":2},"by_repo_kind":{"official":{"samples":14,"ran":12,"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":14,"samples":[{"code_sha256_prefix":"fbaaa371b4ebbafd","entry":"LstmFusion","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fbaaa371b4ebbafd"}},{"code_sha256_prefix":"0261882ecf3d1c25","entry":"PadRNN","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0261882ecf3d1c25"}},{"code_sha256_prefix":"b7f63470f062747e","entry":"PosFeat","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7f63470f062747e"}},{"code_sha256_prefix":"1a652039016eccb4","entry":"ResNet","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a652039016eccb4"}},{"code_sha256_prefix":"59f958c41892d782","entry":"RoiFeatExtractor","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"59f958c41892d782"}},{"code_sha256_prefix":"f350d387d051c671","entry":"SemanticsFeatExtractor","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f350d387d051c671"}},{"code_sha256_prefix":"540e50267a8213fe","entry":"VSFD","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"540e50267a8213fe"}},{"code_sha256_prefix":"71a97abe47fc54dc","entry":"align_feats","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71a97abe47fc54dc"}},{"code_sha256_prefix":"c8c6a98626ee0e88","entry":"align_tokens","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c8c6a98626ee0e88"}},{"code_sha256_prefix":"49abff9073550b42","entry":"conv3x3","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"49abff9073550b42"}},{"code_sha256_prefix":"0e7b2457e7e96b9a","entry":"convert_to_roi_format","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e7b2457e7e96b9a"}},{"code_sha256_prefix":"59c421bb1bb38e71","entry":"tokenize","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"59c421bb1bb38e71"}},{"code_sha256_prefix":"46cf9697f6679bb5","entry":"BasicBlock","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"46cf9697f6679bb5"}},{"code_sha256_prefix":"ad74f969c400615a","entry":"Encoder","repo":"jfma-USTC/HRDoc","repo_kind":"official","path":"end2end_system/strcut_recover/libs/model/encoder.py","file_url":"https://github.com/jfma-USTC/HRDoc/blob/HEAD/end2end_system/strcut_recover/libs/model/encoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad74f969c400615a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}