{"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/a-partition-filter-network-for-joint-entity","title":"A Partition Filter Network for Joint Entity and Relation Extraction","arxiv_id":"2108.12202","date":"2021-08-27","proceeding":"EMNLP 2021 11","authors":["Zhiheng Yan","Chong Zhang","Jinlan Fu","Qi Zhang","Zhongyu Wei"],"abstract":"In joint entity and relation extraction, existing work either sequentially encode task-specific features, leading to an imbalance in inter-task feature interaction where features extracted later have no direct contact with those that come first. Or they encode entity features and relation features in a parallel manner, meaning that feature representation learning for each task is largely independent of each other except for input sharing. We propose a partition filter network to model two-way interaction between tasks properly, where feature encoding is decomposed into two steps: partition and filter. In our encoder, we leverage two gates: entity and relation gate, to segment neurons into two task partitions and one shared partition. The shared partition represents inter-task information valuable to both tasks and is evenly shared across two tasks to ensure proper two-way interaction. The task partitions represent intra-task information and are formed through concerted efforts of both gates, making sure that encoding of task-specific features is dependent upon each other. Experiment results on six public datasets show that our model performs significantly better than previous approaches. In addition, contrary to what previous work has claimed, our auxiliary experiments suggest that relation prediction is contributory to named entity prediction in a non-negligible way. The source code can be found at https://github.com/Coopercoppers/PFN.","url_abs":"https://arxiv.org/abs/2108.12202v8","url_pdf":"https://arxiv.org/pdf/2108.12202v8.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":"a-partition-filter-network-for-joint-entity","repo_url":"https://github.com/Coopercoppers/PFN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"joint-entity-and-relation-extraction","task_name":"Joint Entity and Relation Extraction"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"relation-prediction","task_name":"Relation Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"partition-filter-network","method_name":"Partition Filter Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/joint-entity-and-relation-extraction-on","task":"Joint Entity and Relation Extraction","dataset":"SciERC","model":"PFN","rank_in_archive_order":11,"of":11,"metrics":{"Cross Sentence":"No","Entity F1":"66.8","RE+ Micro F1":"38.4"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ace-2004","task":"Relation Extraction","dataset":"ACE 2004","model":"PFN","rank_in_archive_order":2,"of":11,"metrics":{"Cross Sentence":"No","NER Micro F1":"89.3","RE+ Micro F1":"62.5"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ace-2005","task":"Relation Extraction","dataset":"ACE 2005","model":"PFN","rank_in_archive_order":15,"of":30,"metrics":{"Cross Sentence":"No","NER Micro F1":"89.0","RE+ Micro F1":"66.8","Sentence Encoder":"ALBERT"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ade-corpus-1","task":"Relation Extraction","dataset":"ADE Corpus","model":"PFN","rank_in_archive_order":1,"of":1,"metrics":{"NER Macro F1":"91.3","RE+ Macro F1":"83.2"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ade-corpus","task":"Relation Extraction","dataset":"Adverse Drug Events (ADE) Corpus","model":"PFN (ALBERT XXL, no aggregation)","rank_in_archive_order":4,"of":15,"metrics":{"NER Macro F1":"91.3","RE+ Macro F1":"83.2"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-scierc","task":"Relation Extraction","dataset":"SciERC","model":"PFN","rank_in_archive_order":3,"of":3,"metrics":{"NER Micro F1":"66.8","RE+ Micro F1":"38.4"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-webnlg","task":"Relation Extraction","dataset":"WebNLG","model":"PFN","rank_in_archive_order":2,"of":14,"metrics":{"F1":"93.6","NER Micro F1":"98.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.12202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.12202"}},"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/Coopercoppers/PFN","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"afec84e0faec9423","entry":"LinearDropConnect","repo":"Coopercoppers/PFN","repo_kind":"official","path":"model/pfn.py","file_url":"https://github.com/Coopercoppers/PFN/blob/HEAD/model/pfn.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":"afec84e0faec9423"}},{"code_sha256_prefix":"376d06bf379aaed4","entry":"cumsoftmax","repo":"Coopercoppers/PFN","repo_kind":"official","path":"model/pfn.py","file_url":"https://github.com/Coopercoppers/PFN/blob/HEAD/model/pfn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"376d06bf379aaed4"}},{"code_sha256_prefix":"3ea1177946b16e3f","entry":"encoder","repo":"Coopercoppers/PFN","repo_kind":"official","path":"model/pfn.py","file_url":"https://github.com/Coopercoppers/PFN/blob/HEAD/model/pfn.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":"3ea1177946b16e3f"}},{"code_sha256_prefix":"a9b19a6a9feee024","entry":"ner_unit","repo":"Coopercoppers/PFN","repo_kind":"official","path":"model/pfn.py","file_url":"https://github.com/Coopercoppers/PFN/blob/HEAD/model/pfn.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":"a9b19a6a9feee024"}},{"code_sha256_prefix":"80cd984b7e023533","entry":"re_unit","repo":"Coopercoppers/PFN","repo_kind":"official","path":"model/pfn.py","file_url":"https://github.com/Coopercoppers/PFN/blob/HEAD/model/pfn.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":"80cd984b7e023533"}},{"code_sha256_prefix":"8e459b63dc2fe2eb","entry":"PFN","repo":"Coopercoppers/PFN","repo_kind":"official","path":"model/pfn.py","file_url":"https://github.com/Coopercoppers/PFN/blob/HEAD/model/pfn.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":"8e459b63dc2fe2eb"}},{"code_sha256_prefix":"e41a06253d12c0d0","entry":"pfn_unit","repo":"Coopercoppers/PFN","repo_kind":"official","path":"model/pfn.py","file_url":"https://github.com/Coopercoppers/PFN/blob/HEAD/model/pfn.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":"e41a06253d12c0d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}