{"id":13512684,"url":"https://github.com/XueFuzhao/GDPNet","last_synced_at":"2025-03-31T00:30:39.981Z","repository":{"id":118646142,"uuid":"319311847","full_name":"XueFuzhao/GDPNet","owner":"XueFuzhao","description":null,"archived":false,"fork":false,"pushed_at":"2022-12-11T22:32:52.000Z","size":1060,"stargazers_count":38,"open_issues_count":3,"forks_count":13,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-29T07:33:33.205Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/XueFuzhao.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-12-07T12:24:21.000Z","updated_at":"2024-05-21T02:41:10.000Z","dependencies_parsed_at":null,"dependency_job_id":"d5ad7dcb-91b0-4101-b821-0e4ac07c6f70","html_url":"https://github.com/XueFuzhao/GDPNet","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/XueFuzhao%2FGDPNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XueFuzhao%2FGDPNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XueFuzhao%2FGDPNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XueFuzhao%2FGDPNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/XueFuzhao","download_url":"https://codeload.github.com/XueFuzhao/GDPNet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246399816,"owners_count":20770907,"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":"2024-08-01T04:00:28.670Z","updated_at":"2025-03-31T00:30:39.956Z","avatar_url":"https://github.com/XueFuzhao.png","language":"Python","funding_links":[],"categories":["Papers","关系抽取、信息抽取"],"sub_categories":["Supervised Approaches","其他_文本生成、文本对话"],"readme":"# GDPNet\n\nGDPNet: Refining Refining Latent Multi-View Graph for Relation Extraction\n\nThe code is divided into two parts, DialogRE and TACRED, by datasets.\n\n# Requirements\n\nPyTorch \u003e= 1.4\n\nCUDA == 10.1\n\nApex\n\nWe perform our experiments on GTX 1070 GPU. Please use the same hardware and software environment if possible to ensure the same results.\n\nThe model on GTX 1070 GPU has been released: https://drive.google.com/drive/folders/1eod1YmMP6pcVU4-7vTIIqE0oVOUrBERG?usp=sharing\n\nWe also reproduced our results on Q8000 GPU, and V100 GPU. \n\nThe model on Q8000 GPU has been released: https://drive.google.com/drive/folders/1CMXmO8_hqB1L_Z6zfJuQ2g56tKqTq_y7?usp=sharing\n\nThe model on V100 GPU has been released: https://drive.google.com/drive/folders/1lU5SAmclacFtgqX5I3qmhGXR1RnZoAZg?usp=sharing\n\n\n# DialogRE\n\nThis dataset can be downloaded at: https://github.com/nlpdata/dialogre\n\nDownload and unzip BERT from https://github.com/google-research/bert, and set up the environment variable for BERT by export BERT_BASE_DIR=/PATH/TO/BERT/DIR in every run_GDPNet.sh.\n\nWe also provide the **BERT-base-uncased** (PyTorch Version): https://drive.google.com/drive/folders/1qBzjWDVpXSBXfmxO6yW6ATBX3D7LW5YZ?usp=sharing\n\n(1) Please copy the *.json files into DialogRE/data\n\n(2) Train the GDPNet model\n```sh\n$ cd GDPNet\n$ bash run_GDPNet.sh\n```\n\nNote: we also provided the logits_dev.txt and logits_test.txt, so we can run the last line of run_GDPNet.sh to see the results directly. Please copy the files in https://drive.google.com/drive/folders/1CMXmO8_hqB1L_Z6zfJuQ2g56tKqTq_y7?usp=sharing into GDPNet/DialogRE/GDPNet\n\n\n\n# TACRED\n\nTACRED URL: https://nlp.stanford.edu/projects/tacred/\n\nTACRED-Revisit URL: https://github.com/DFKI-NLP/tacrev/\n\n(1) Please download the TACRED and TACRED-Revisit and copy them into GDPNet/tacred and GDPNet/tacred_revisit respectively.\n\n    TACRED URL: https://nlp.stanford.edu/projects/tacred/\n    \n    TACRED-Revisit URL: https://github.com/DFKI-NLP/tacrev/\n\n(2) Train the GDPNet model\n\nNote: We use SpanBERT large as the backbone of BERT module.\n\n```sh\n$ cd GDPNet\n$ bash run.sh\n```\n\nNote: The default dataset is TACRED, pls change the --data_dir in run.sh to try TACRED-revisit\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXueFuzhao%2FGDPNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FXueFuzhao%2FGDPNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXueFuzhao%2FGDPNet/lists"}