{"id":13595163,"url":"https://github.com/jiesutd/LatticeLSTM","last_synced_at":"2025-04-09T10:32:56.952Z","repository":{"id":46167951,"uuid":"130574794","full_name":"jiesutd/LatticeLSTM","owner":"jiesutd","description":"Chinese NER using Lattice LSTM. Code for ACL 2018 paper.","archived":false,"fork":false,"pushed_at":"2019-04-25T14:44:32.000Z","size":338,"stargazers_count":1808,"open_issues_count":12,"forks_count":452,"subscribers_count":40,"default_branch":"master","last_synced_at":"2025-04-08T13:01:53.726Z","etag":null,"topics":["chinese-ner","lattice-lstm","lattice-lstm-crf","lstm-crf","ner"],"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/jiesutd.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}},"created_at":"2018-04-22T14:23:20.000Z","updated_at":"2025-04-05T03:19:45.000Z","dependencies_parsed_at":"2022-08-12T12:40:49.786Z","dependency_job_id":null,"html_url":"https://github.com/jiesutd/LatticeLSTM","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiesutd%2FLatticeLSTM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiesutd%2FLatticeLSTM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiesutd%2FLatticeLSTM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jiesutd%2FLatticeLSTM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jiesutd","download_url":"https://codeload.github.com/jiesutd/LatticeLSTM/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248020593,"owners_count":21034459,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["chinese-ner","lattice-lstm","lattice-lstm-crf","lstm-crf","ner"],"created_at":"2024-08-01T16:01:45.102Z","updated_at":"2025-04-09T10:32:56.914Z","avatar_url":"https://github.com/jiesutd.png","language":"Python","funding_links":[],"categories":["Python","实体识别NER、意图识别、槽位填充"],"sub_categories":["其他_文本生成、文本对话"],"readme":"Chinese NER Using Lattice LSTM\n====\n\nLattice LSTM for Chinese NER. Character based LSTM with Lattice embeddings as input.\n\nModels and results can be found at our ACL 2018 paper [Chinese NER Using Lattice LSTM](https://arxiv.org/pdf/1805.02023.pdf). It achieves 93.18% F1-value on MSRA dataset, which is the state-of-the-art result on Chinese NER task.\n\nDetails will be updated soon.\n\nRequirement:\n======\n\tPython: 2.7   \n\tPyTorch: 0.3.0 \n(for PyTorch 0.3.1, please refer [issue#8](https://github.com/jiesutd/LatticeLSTM/issues/8) for a slight modification.)\n\nInput format:\n======\nCoNLL format (prefer BIOES tag scheme), with each character its label for one line. Sentences are splited with a null line.\n\n\t美\tB-LOC\n\t国\tE-LOC\n\t的\tO\n\t华\tB-PER\n\t莱\tI-PER\n\t士\tE-PER\n\n\t我\tO\n\t跟\tO\n\t他\tO\n\t谈\tO\n\t笑\tO\n\t风\tO\n\t生\tO \n\nPretrained Embeddings:\n====\nThe pretrained character and word embeddings are the same with the embeddings in the baseline of [RichWordSegmentor](https://github.com/jiesutd/RichWordSegmentor)\n\nCharacter embeddings (gigaword_chn.all.a2b.uni.ite50.vec): [Google Drive](https://drive.google.com/file/d/1_Zlf0OAZKVdydk7loUpkzD2KPEotUE8u/view?usp=sharing) or [Baidu Pan](https://pan.baidu.com/s/1pLO6T9D)\n\nWord(Lattice) embeddings (ctb.50d.vec): [Google Drive](https://drive.google.com/file/d/1K_lG3FlXTgOOf8aQ4brR9g3R40qi1Chv/view?usp=sharing) or [Baidu Pan](https://pan.baidu.com/s/1pLO6T9D)\n\nHow to run the code?\n====\n1. Download the character embeddings and word embeddings and put them in the `data` folder.\n2. Modify the `run_main.py` or `run_demo.py` by adding your train/dev/test file directory.\n3. `sh run_main.py` or `sh run_demo.py`\n\n\nResume NER data \n====\nCrawled from the Sina Finance, it includes the resumes of senior executives from listed companies in the Chinese stock market. Details can be found in our paper.\n\n\nCite: \n========\nPlease cite our ACL 2018 paper:\n\n    @article{zhang2018chinese,  \n     title={Chinese NER Using Lattice LSTM},  \n     author={Yue Zhang and Jie Yang},  \n     booktitle={Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)},\n     year={2018}  \n    }","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjiesutd%2FLatticeLSTM","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjiesutd%2FLatticeLSTM","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjiesutd%2FLatticeLSTM/lists"}