{"id":48487413,"url":"https://github.com/brightjade/prism","last_synced_at":"2026-04-07T10:03:59.466Z","repository":{"id":205415020,"uuid":"691454016","full_name":"brightjade/PRiSM","owner":"brightjade","description":"Source code for paper \"PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration\", Findings of IJCNLP-AACL 2023","archived":false,"fork":false,"pushed_at":"2023-11-04T07:00:28.000Z","size":25,"stargazers_count":8,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-01-29T15:47:10.229Z","etag":null,"topics":["calibration","document-level","document-level-relation-extraction","low-resource","relation-extraction"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/brightjade.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-09-14T07:59:20.000Z","updated_at":"2023-12-02T11:53:11.000Z","dependencies_parsed_at":null,"dependency_job_id":"865d8a6d-716d-4d47-b1e5-a5ff6c259fca","html_url":"https://github.com/brightjade/PRiSM","commit_stats":null,"previous_names":["brightjade/prism"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/brightjade/PRiSM","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brightjade%2FPRiSM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brightjade%2FPRiSM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brightjade%2FPRiSM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brightjade%2FPRiSM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/brightjade","download_url":"https://codeload.github.com/brightjade/PRiSM/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brightjade%2FPRiSM/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31508282,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T03:10:19.677Z","status":"ssl_error","status_checked_at":"2026-04-07T03:10:13.982Z","response_time":105,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["calibration","document-level","document-level-relation-extraction","low-resource","relation-extraction"],"created_at":"2026-04-07T10:03:58.811Z","updated_at":"2026-04-07T10:03:59.461Z","avatar_url":"https://github.com/brightjade.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PRiSM\n\nSource code for our *Findings of IJCNLP-AACL 2023* paper [PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration](https://arxiv.org/abs/2309.13869).\n\n## Requirements\n\n- Python (tested on 3.8.16)\n- CUDA (tested on 11.7)\n- PyTorch (tested on 1.13.1)\n- Transformers (tested on 4.30.0)\n- numpy (tested on 1.22.4)\n- wandb\n- tqdm\n\n## Datasets\n\nDatasets can be downloaded here: [DocRED](https://drive.google.com/drive/folders/1c5-0YwnoJx8NS6CV2f-NoTHR__BdkNqw), [Re-DocRED](https://github.com/tonytan48/Re-DocRED), [DWIE](https://github.com/klimzaporojets/DWIE). The expected structure of files is:\n\n```\n[working directory]\n |-- data\n |    |-- DocRED\n |    |    |-- train_distant.json        \n |    |    |-- train.json\n |    |    |-- dev.json\n |    |    |-- test.json\n |    |    |-- label_map.json\n |    |    |-- rel_info.json\n |    |    |-- rel_desc.json\n |    |-- Re-DocRED\n |    |    |-- train_distant.json        \n |    |    |-- train.json\n |    |    |-- dev.json\n |    |    |-- test.json\n |    |    |-- label_map.json\n |    |    |-- rel_info.json\n |    |    |-- rel_desc.json\n |    |-- DWIE\n |    |    |-- train/\n |    |    |-- dev/\n |    |    |-- test/\n |    |    |-- label_map.json\n |    |    |-- rel_desc.json\n```\n\n## Training and Evaluation\n\nTrain the model with the following command:\n\n```bash\n\u003e\u003e bash scripts/train.sh\n```\n\nEvaluate the model with the following command:\n\n```bash\n\u003e\u003e bash scripts/evaluate.sh\n```\n\n## Citation\n\nIf you make use of this code in your work, please kindly cite our paper:\n\n```bibtex\n@inproceedings{choi2023prism,\n               author={Choi, Minseok and Lim, Hyesu and Choo, Jaegul},\n               title={P{R}i{S}{M}: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration},\n               booktitle={Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},\n               month={November},\n               year={2023},\n               address={Nusa Dua, Bali},\n               publisher={Association for Computational Linguistics},\n               pages={39--47},\n               url={https://aclanthology.org/2023.findings-ijcnlp.4}\n}\n```\n\n## Acknowledgements\n\nThis work was supported by Institute of Information \u0026 communications Technology Planning \u0026 Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2019-0-00075, Artificial Intelligence Graduate School Program (KAIST)), the National Supercomputing Center with supercomputing resources including technical support (KSC-2022-CRE-0312), and Samsung Electronics Co., Ltd.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrightjade%2Fprism","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbrightjade%2Fprism","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrightjade%2Fprism/lists"}