{"id":28676540,"url":"https://github.com/zjunlp/doced","last_synced_at":"2026-02-26T07:48:39.527Z","repository":{"id":51200208,"uuid":"354552254","full_name":"zjunlp/DocED","owner":"zjunlp","description":"[ACL 2021] MLBiNet: A Cross-Sentence Collective Event Detection Network","archived":false,"fork":false,"pushed_at":"2022-01-10T06:19:46.000Z","size":17886,"stargazers_count":35,"open_issues_count":0,"forks_count":6,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-01-31T23:21:36.786Z","etag":null,"topics":["cross-sentence","event-detection","event-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/zjunlp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2021-04-04T13:35:31.000Z","updated_at":"2024-03-04T15:07:32.000Z","dependencies_parsed_at":"2022-08-28T02:00:40.247Z","dependency_job_id":null,"html_url":"https://github.com/zjunlp/DocED","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zjunlp/DocED","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjunlp%2FDocED","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjunlp%2FDocED/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjunlp%2FDocED/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjunlp%2FDocED/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zjunlp","download_url":"https://codeload.github.com/zjunlp/DocED/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjunlp%2FDocED/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29851861,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-25T22:37:40.667Z","status":"online","status_checked_at":"2026-02-26T02:00:06.774Z","response_time":89,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["cross-sentence","event-detection","event-extraction"],"created_at":"2025-06-13T23:05:04.144Z","updated_at":"2026-02-26T07:48:39.500Z","avatar_url":"https://github.com/zjunlp.png","language":"Python","readme":"# DocED\nThis repository is the official implementation of the ACL 2021 paper [MLBiNet: A Cross-Sentence Collective Event Detection Network](https://arxiv.org/pdf/2105.09458v1.pdf).\n\n## Requirements\n### To install basic requirements:\npip install requirements.txt\n\n## Datasets\nACE2005 can be found here: https://catalog.ldc.upenn.edu/LDC2006T06\n\n## Basic training\n### To evaluate a setting with serveral random trials, execute\npython run_experiments_multi.py\n\n#### Main hyperparameters in train_MLBiNet.py include:\n--tagging_mechanism,   mechanism to model event inter-dependency, you can choose one of \"forward_decoder\", \"backward_decoder\" or \"bidirectional_decoder\"\n\n--num_tag_layers,   number of tagging layers, 1 indicates that we do sentence-level ED, 2 indicates that information of adjacent sentences were aggregated, ...\n\n--max_doc_len,   maximum number of consecutive sentences are extracted as a mini-document, we can set it as 8 or 16\n\n--tag_dim,   dimension of an uni-directional event tagging vector\n\n--self_att_not,   whether to apply self-attention mechanism in sentence encoder \n\n## Main results\n### Overall performance on ACE2005\n![image](https://user-images.githubusercontent.com/32415352/118842889-252e6900-b8fc-11eb-9de8-dba5f82377f4.png)\n\n### Performance on detecting multiple events collectively\n![image](https://user-images.githubusercontent.com/32415352/118843522-b9003500-b8fc-11eb-8e3f-759f6d37f98a.png)\n\nwhere 1/1 means one sentence that has one event; otherwise, 1/n is used.\n\n### Performance of our proposed method with different multi-layer settings or decoder methods\n![image](https://user-images.githubusercontent.com/32415352/118843910-11cfcd80-b8fd-11eb-965c-fbcde1319983.png)\n\n## How to Cite\n\n```bibtex\n@inproceedings{ACL2021_MLBiNet,\n  author    = {Dongfang Lou and\n               Zhilin Liao and\n               Shumin Deng and\n               Ningyu Zhang and\n               Huajun Chen},\n  title     = {MLBiNet: A Cross-Sentence Collective Event Detection Network},\n  booktitle = {{ACL}},\n  publisher = {Association for Computational Linguistics},\n  year      = {2021}\n}\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzjunlp%2Fdoced","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzjunlp%2Fdoced","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzjunlp%2Fdoced/lists"}