{"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/schema-aware-reference-as-prompt-improves","title":"Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction","arxiv_id":"2210.10709","date":"2022-10-19","proceeding":null,"authors":["Yunzhi Yao","Shengyu Mao","Ningyu Zhang","Xiang Chen","Shumin Deng","Xi Chen","Huajun Chen"],"abstract":"With the development of pre-trained language models, many prompt-based approaches to data-efficient knowledge graph construction have been proposed and achieved impressive performance. However, existing prompt-based learning methods for knowledge graph construction are still susceptible to several potential limitations: (i) semantic gap between natural language and output structured knowledge with pre-defined schema, which means model cannot fully exploit semantic knowledge with the constrained templates; (ii) representation learning with locally individual instances limits the performance given the insufficient features, which are unable to unleash the potential analogical capability of pre-trained language models. Motivated by these observations, we propose a retrieval-augmented approach, which retrieves schema-aware Reference As Prompt (RAP), for data-efficient knowledge graph construction. It can dynamically leverage schema and knowledge inherited from human-annotated and weak-supervised data as a prompt for each sample, which is model-agnostic and can be plugged into widespread existing approaches. Experimental results demonstrate that previous methods integrated with RAP can achieve impressive performance gains in low-resource settings on five datasets of relational triple extraction and event extraction for knowledge graph construction. Code is available in https://github.com/zjunlp/RAP.","url_abs":"https://arxiv.org/abs/2210.10709v5","url_pdf":"https://arxiv.org/pdf/2210.10709v5.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":"schema-aware-reference-as-prompt-improves","repo_url":"https://github.com/zjunlp/RAP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"event-extraction","task_name":"Event Extraction"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"graph-construction","task_name":"graph construction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.10709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10709"}},"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/zjunlp/RAP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":10},"by_repo_kind":{"official":{"samples":11,"ran":1,"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":"97a3eca137c3440e","entry":"find_sublist_index","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/RelationPrompt/utils.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/RelationPrompt/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97a3eca137c3440e"}},{"code_sha256_prefix":"6adefb5e4abb5be2","entry":"find_head_idx","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/PRGC/dataloader_utils.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/PRGC/dataloader_utils.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":"6adefb5e4abb5be2"}},{"code_sha256_prefix":"489e40f0d2ef6927","entry":"find_sublist_indices","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/RelationPrompt/utils.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/RelationPrompt/utils.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":"489e40f0d2ef6927"}},{"code_sha256_prefix":"9d4067b23a01fee1","entry":"get_chunk_type","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/PRGC/metrics.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/PRGC/metrics.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":"9d4067b23a01fee1"}},{"code_sha256_prefix":"68b3cc3a2577fbd6","entry":"get_chunks","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/PRGC/metrics.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/PRGC/metrics.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":"68b3cc3a2577fbd6"}},{"code_sha256_prefix":"626bdc34ef9914c2","entry":"get_metrics","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/PRGC/evaluate.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/PRGC/evaluate.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":"626bdc34ef9914c2"}},{"code_sha256_prefix":"1d6af4e45a421828","entry":"load_checkpoint","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/PRGC/utils.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/PRGC/utils.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":"1d6af4e45a421828"}},{"code_sha256_prefix":"0b33d061e8b7d42d","entry":"load_wiki_relation_map","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/RelationPrompt/utils.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/RelationPrompt/utils.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":"0b33d061e8b7d42d"}},{"code_sha256_prefix":"7edec986d793594c","entry":"read_examples","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/PRGC/dataloader_utils.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/PRGC/dataloader_utils.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":"7edec986d793594c"}},{"code_sha256_prefix":"94ab66ec54e9046e","entry":"span2str","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/PRGC/evaluate.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/PRGC/evaluate.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":"94ab66ec54e9046e"}},{"code_sha256_prefix":"b38b4069b22679d0","entry":"tag_mapping_nearest","repo":"zjunlp/RAP","repo_kind":"official","path":"BaseModel/PRGC/metrics.py","file_url":"https://github.com/zjunlp/RAP/blob/HEAD/BaseModel/PRGC/metrics.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":"b38b4069b22679d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}