{"id":13754356,"url":"https://github.com/cuhksz-nlp/RE-TaMM","last_synced_at":"2025-05-09T22:31:57.927Z","repository":{"id":112576727,"uuid":"370763642","full_name":"cuhksz-nlp/RE-TaMM","owner":"cuhksz-nlp","description":null,"archived":false,"fork":false,"pushed_at":"2022-12-23T08:35:12.000Z","size":1935,"stargazers_count":15,"open_issues_count":6,"forks_count":6,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-11-16T07:33:24.580Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cuhksz-nlp.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-05-25T16:44:12.000Z","updated_at":"2024-03-04T07:12:59.000Z","dependencies_parsed_at":"2023-05-16T18:45:46.034Z","dependency_job_id":null,"html_url":"https://github.com/cuhksz-nlp/RE-TaMM","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/cuhksz-nlp%2FRE-TaMM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cuhksz-nlp%2FRE-TaMM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cuhksz-nlp%2FRE-TaMM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cuhksz-nlp%2FRE-TaMM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cuhksz-nlp","download_url":"https://codeload.github.com/cuhksz-nlp/RE-TaMM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253335823,"owners_count":21892744,"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":[],"created_at":"2024-08-03T09:01:56.548Z","updated_at":"2025-05-09T22:31:52.919Z","avatar_url":"https://github.com/cuhksz-nlp.png","language":"Python","funding_links":[],"categories":["关系抽取、信息抽取"],"sub_categories":["其他_文本生成、文本对话"],"readme":"# RE-TaMM\n\nThis is the implementation of [Relation Extraction with Type-aware Map Memories of Word Dependencies](https://aclanthology.org/2021.findings-acl.221.pdf) at ACL 2021.\n\nYou can e-mail Yuanhe Tian at `yhtian@uw.edu`, if you have any questions.\n\n\n**Visit our [homepage](https://github.com/synlp/.github) to find more our recent research and softwares for NLP (e.g., pre-trained LM, POS tagging, NER, sentiment analysis, relation extraction, datasets, etc.).**\n\n## Upgrades of RE-TaMM\n\nWe are improving our RE-TaMM. For updates, please visit [HERE](https://github.com/synlp/RE-TaMM).\n\n## Citation\n\nIf you use or extend our work, please cite our paper at ACL 2021.\n\n```\n@article{chen2021relation,\n  title={Relation Extraction with Type-aware Map Memories of Word Dependencies},\n  author={Chen, Guimin and Tian, Yuanhe and Song, Yan and Wan, Xiang},\n  journal={Findings of the Association for Computational Linguistics: ACLIJCNLP},\n  year={2021}\n}\n```\n\n## Requirements\n\nOur code works with the following environment.\n* `python\u003e=3.7`\n* `pytorch\u003e=1.3`\n\n## Dataset\n\nTo obtain the data, you can go to [`data`](./data) directory for details.\n\n## Downloading BERT and RE-TaMM\n\nIn our paper, we use BERT ([paper](https://www.aclweb.org/anthology/N19-1423/)) as the encoder.\n\nFor BERT, please download pre-trained BERT-Base and BERT-Large English from [Google](https://github.com/google-research/bert) or from [HuggingFace](https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese.tar.gz). If you download it from Google, you need to convert the model from TensorFlow version to PyTorch version.\n\nFor RE-TAMM, you can download the models we trained in our experiments from [Google Drive](https://drive.google.com/drive/folders/1NqN2S9VGbgmD6Z-V2YVncA9lHOaffOuM?usp=sharing).\n\n## Run on Sample Data\n\nRun `run_sample.sh` to train a model on the small sample data under the `sample_data` directory.\n\n## Training and Testing\n\nYou can find the command lines to train and test models in `run_train.sh` and `run_test.sh`, respectively.\n\nHere are some important parameters:\n\n* `--do_train`: train the model.\n* `--do_eval`: test the model.\n\n## To-do List\n\n* Regular maintenance.\n\nYou can leave comments in the `Issues` section, if you want us to implement any functions.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcuhksz-nlp%2FRE-TaMM","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcuhksz-nlp%2FRE-TaMM","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcuhksz-nlp%2FRE-TaMM/lists"}