{"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/rexel-an-end-to-end-model-for-document-level","title":"REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking","arxiv_id":"2404.12788","date":"2024-04-19","proceeding":null,"authors":["Nacime Bouziani","Shubhi Tyagi","Joseph Fisher","Jens Lehmann","Andrea Pierleoni"],"abstract":"Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by closed information extraction (cIE). However, existing approaches for cIE suffer from two limitations: (i) they are often pipelines which makes them prone to error propagation, and/or (ii) they are restricted to sentence level which prevents them from capturing long-range dependencies and results in expensive inference time. We address these limitations by proposing REXEL, a highly efficient and accurate model for the joint task of document level cIE (DocIE). REXEL performs mention detection, entity typing, entity disambiguation, coreference resolution and document-level relation classification in a single forward pass to yield facts fully linked to a reference knowledge graph. It is on average 11 times faster than competitive existing approaches in a similar setting and performs competitively both when optimised for any of the individual subtasks and a variety of combinations of different joint tasks, surpassing the baselines by an average of more than 6 F1 points. The combination of speed and accuracy makes REXEL an accurate cost-efficient system for extracting structured information at web-scale. We also release an extension of the DocRED dataset to enable benchmarking of future work on DocIE, which is available at https://github.com/amazon-science/e2e-docie.","url_abs":"https://arxiv.org/abs/2404.12788v1","url_pdf":"https://arxiv.org/pdf/2404.12788v1.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":"rexel-an-end-to-end-model-for-document-level","repo_url":"https://github.com/amazon-science/e2e-docie","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"document-level-closed-information-extraction","task_name":"Document-level Closed Information Extraction"},{"task_slug":"document-level-relation-extraction","task_name":"Document-level Relation Extraction"},{"task_slug":"entity-disambiguation","task_name":"Entity Disambiguation"},{"task_slug":"entity-linking","task_name":"Entity Linking"},{"task_slug":"entity-retrieval","task_name":"Entity Retrieval"},{"task_slug":"entity-typing","task_name":"Entity Typing"},{"task_slug":"joint-entity-and-relation-extraction","task_name":"Joint Entity and Relation Extraction"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-classification","task_name":"Relation Classification"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[{"slug":"docred-ie","name":"DocRED-IE","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/coreference-resolution-on-dwie","task":"Coreference Resolution","dataset":"DWIE","model":"REXEL","rank_in_archive_order":1,"of":3,"metrics":{"Avg. F1":"95.12"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-docred-ie","task":"Coreference Resolution","dataset":"DocRED-IE","model":"REXEL","rank_in_archive_order":1,"of":1,"metrics":{"Avg F1":"90.93"},"uses_additional_data":false},{"leaderboard":"/sota/document-level-closed-information-extraction-1","task":"Document-level Closed Information Extraction","dataset":"DWIE","model":"REXEL","rank_in_archive_order":1,"of":1,"metrics":{"F1-Hard":"53.77"},"uses_additional_data":false},{"leaderboard":"/sota/document-level-closed-information-extraction","task":"Document-level Closed Information Extraction","dataset":"DocRED","model":"REXEL","rank_in_archive_order":1,"of":1,"metrics":{"Relation F1":"27.96"},"uses_additional_data":false},{"leaderboard":"/sota/document-level-closed-information-extraction-2","task":"Document-level Closed Information Extraction","dataset":"DocRED-IE","model":"REXEL","rank_in_archive_order":1,"of":1,"metrics":{"Relation F1":"27.96"},"uses_additional_data":false},{"leaderboard":"/sota/document-level-relation-extraction-on-docred-3","task":"Document-level Relation Extraction","dataset":"DocRED-IE","model":"REXEL","rank_in_archive_order":1,"of":1,"metrics":{"Relation F1":"60.10"},"uses_additional_data":false},{"leaderboard":"/sota/entity-disambiguation-on-docred-ie","task":"Entity Disambiguation","dataset":"DocRED-IE","model":"REXEL","rank_in_archive_order":1,"of":1,"metrics":{"Avg F1":"86.74"},"uses_additional_data":false},{"leaderboard":"/sota/entity-typing-on-docred-ie","task":"Entity Typing","dataset":"DocRED-IE","model":"REXEL","rank_in_archive_order":1,"of":1,"metrics":{"Avg F1":"96.01"},"uses_additional_data":false},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-3","task":"Joint Entity and Relation Extraction","dataset":"DocRED","model":"REXEL","rank_in_archive_order":5,"of":6,"metrics":{"Relation F1":"39.06"},"uses_additional_data":false},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-10","task":"Joint Entity and Relation Extraction","dataset":"DocRED-IE","model":"REXEL","rank_in_archive_order":1,"of":1,"metrics":{"Relation F1":"39.06"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-dwie","task":"Named Entity Recognition (NER)","dataset":"DWIE","model":"REXEL","rank_in_archive_order":1,"of":3,"metrics":{"F1-Hard":"90.59"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-dwie","task":"Relation Extraction","dataset":"DWIE","model":"REXEL","rank_in_archive_order":1,"of":3,"metrics":{"F1-Hard":"65.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.12788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12788"}},"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/lavis-nlp/jerex","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3},"by_repo_kind":{"found_in_text":{"samples":3,"ran":3,"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":"6f7e402bf2d503c6","entry":"create_directories_dir","repo":"lavis-nlp/jerex","repo_kind":"found_in_text","path":"jerex/util.py","file_url":"https://github.com/lavis-nlp/jerex/blob/HEAD/jerex/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f7e402bf2d503c6"}},{"code_sha256_prefix":"e027b954ff8541cc","entry":"create_directories_file","repo":"lavis-nlp/jerex","repo_kind":"found_in_text","path":"jerex/util.py","file_url":"https://github.com/lavis-nlp/jerex/blob/HEAD/jerex/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e027b954ff8541cc"}},{"code_sha256_prefix":"09521c76d9725784","entry":"extend_tensor","repo":"lavis-nlp/jerex","repo_kind":"found_in_text","path":"jerex/util.py","file_url":"https://github.com/lavis-nlp/jerex/blob/HEAD/jerex/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"09521c76d9725784"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}