{"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/hyspa-hybrid-span-generation-for-scalable","title":"HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction","arxiv_id":"2106.15838","date":"2021-06-30","proceeding":"Findings (ACL) 2021 8","authors":["Liliang Ren","Chenkai Sun","Heng Ji","Julia Hockenmaier"],"abstract":"Text-to-Graph extraction aims to automatically extract information graphs consisting of mentions and types from natural language texts. Existing approaches, such as table filling and pairwise scoring, have shown impressive performance on various information extraction tasks, but they are difficult to scale to datasets with longer input texts because of their second-order space/time complexities with respect to the input length. In this work, we propose a Hybrid Span Generator (HySPA) that invertibly maps the information graph to an alternating sequence of nodes and edge types, and directly generates such sequences via a hybrid span decoder which can decode both the spans and the types recurrently in linear time and space complexities. Extensive experiments on the ACE05 dataset show that our approach also significantly outperforms state-of-the-art on the joint entity and relation extraction task.","url_abs":"https://arxiv.org/abs/2106.15838v1","url_pdf":"https://arxiv.org/pdf/2106.15838v1.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":"hyspa-hybrid-span-generation-for-scalable","repo_url":"https://github.com/renll/HySPA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"joint-entity-and-relation-extraction","task_name":"Joint Entity and Relation Extraction"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/relation-extraction-on-ace-2005","task":"Relation Extraction","dataset":"ACE 2005","model":"HySPA (ours) w/ RoBERTa","rank_in_archive_order":29,"of":30,"metrics":{"Relation F1":"68.2"},"uses_additional_data":false},{"leaderboard":"/sota/relation-extraction-on-ace-2005","task":"Relation Extraction","dataset":"ACE 2005","model":"HySPA","rank_in_archive_order":30,"of":30,"metrics":{"Cross Sentence":"No","Sentence Encoder":"ALBERT"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.15838","atlas_url":"https://app.syntology.ai/?focus=2106.15838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.15838"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/dwadden/dygiepp","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"found_in_text":{"samples":5,"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":"bbc5dc5142133340","entry":"batch_identity","repo":"dwadden/dygiepp","repo_kind":"found_in_text","path":"dygie/models/shared.py","file_url":"https://github.com/dwadden/dygiepp/blob/HEAD/dygie/models/shared.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":"bbc5dc5142133340"}},{"code_sha256_prefix":"fada67a6d1459131","entry":"compute_f1","repo":"dwadden/dygiepp","repo_kind":"found_in_text","path":"dygie/training/f1.py","file_url":"https://github.com/dwadden/dygiepp/blob/HEAD/dygie/training/f1.py","link_basis":"harvester_set","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":"fada67a6d1459131"}},{"code_sha256_prefix":"7e0b52001d4f5323","entry":"cumsum_shifted","repo":"dwadden/dygiepp","repo_kind":"found_in_text","path":"dygie/models/shared.py","file_url":"https://github.com/dwadden/dygiepp/blob/HEAD/dygie/models/shared.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":"7e0b52001d4f5323"}},{"code_sha256_prefix":"1b01fb249fb7cd71","entry":"fields_to_batches","repo":"dwadden/dygiepp","repo_kind":"found_in_text","path":"dygie/models/shared.py","file_url":"https://github.com/dwadden/dygiepp/blob/HEAD/dygie/models/shared.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":"1b01fb249fb7cd71"}},{"code_sha256_prefix":"ac4edaf53cf349f7","entry":"safe_div","repo":"dwadden/dygiepp","repo_kind":"found_in_text","path":"dygie/training/f1.py","file_url":"https://github.com/dwadden/dygiepp/blob/HEAD/dygie/training/f1.py","link_basis":"harvester_set","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":"ac4edaf53cf349f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}