{"id":19467611,"url":"https://github.com/thunlp/kernelgat","last_synced_at":"2025-07-31T11:05:50.231Z","repository":{"id":35228175,"uuid":"216730564","full_name":"thunlp/KernelGAT","owner":"thunlp","description":"The source codes for Fine-grained Fact Verification with Kernel Graph Attention Network.","archived":false,"fork":false,"pushed_at":"2022-12-08T10:24:37.000Z","size":2374,"stargazers_count":180,"open_issues_count":5,"forks_count":37,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-06-25T09:05:59.488Z","etag":null,"topics":["fact-verification","graph-attention-network","kernel"],"latest_commit_sha":null,"homepage":"","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/thunlp.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}},"created_at":"2019-10-22T05:32:42.000Z","updated_at":"2025-02-24T11:31:39.000Z","dependencies_parsed_at":"2023-01-15T16:34:29.790Z","dependency_job_id":null,"html_url":"https://github.com/thunlp/KernelGAT","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/thunlp/KernelGAT","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thunlp%2FKernelGAT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thunlp%2FKernelGAT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thunlp%2FKernelGAT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thunlp%2FKernelGAT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/thunlp","download_url":"https://codeload.github.com/thunlp/KernelGAT/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/thunlp%2FKernelGAT/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268026083,"owners_count":24183333,"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","status":"online","status_checked_at":"2025-07-31T02:00:08.723Z","response_time":66,"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":["fact-verification","graph-attention-network","kernel"],"created_at":"2024-11-10T18:36:13.039Z","updated_at":"2025-07-31T11:05:50.185Z","avatar_url":"https://github.com/thunlp.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Kernel Graph Attention Network (KGAT)\nThere are source codes for [Fine-grained Fact Verification with Kernel Graph Attention Network](https://www.aclweb.org/anthology/2020.acl-main.655.pdf).\n\n![model](https://github.com/thunlp/KernelGAT/blob/master/model.png)\n\nFor more information about the FEVER 1.0 shared task can be found on this [website](http://fever.ai).\n\n## 😃 What's New\n[Fact Extraction and Verification with SCIFACT](https://scifact.apps.allenai.org)\n\nThe shared task introduces scientific claim verification for helping scientists, clinicians, and public to verify the credibility of such claims with scientific literature, especially for the claims related to COVID-19. \\\n  [\u003e\u003e Reproduce Our Results](./scikgat) [\u003e\u003e About SCIFACT Dataset](https://www.aclweb.org/anthology/2020.emnlp-main.609.pdf) [\u003e\u003e Our Paper](https://www.aclweb.org/anthology/2020.findings-emnlp.216)\n\n\n## Requirement\n* Python 3.X\n* fever_score\n* Pytorch\n* pytorch_pretrained_bert\n* transformers\n\n\n## Data and Checkpoint\n* All data and BERT based chechpoints can be found at [Ali Drive](https://thunlp.oss-cn-qingdao.aliyuncs.com/KernelGAT/FEVER/KernelGAT.zip).\n* RoBERTa based models and chechpoints can be found at [Ali Drive](https://thunlp.oss-cn-qingdao.aliyuncs.com/KernelGAT/FEVER/KernelGAT_roberta_large.zip).\n\n## Retrieval Model\n* BERT based ranker.\n* Go to the ``retrieval_model`` folder for more information.\n\n\n## Pretrain Model\n* Pre-train BERT with claim-evidence pairs.\n* Go to the ``pretrain`` folder for more information.\n\n\n## KGAT Model\n* Our KGAT model.\n* Go to the ``kgat`` folder for more information.\n\n\n## Results\nThe results are all on [Codalab leaderboard](https://competitions.codalab.org/competitions/18814#results).\n\n\n| User | Pre-train Model| Label Accuracy| FEVER Score |\n| -------- | -------- | --------  | --------  |\n[GEAR_single](https://arxiv.org/pdf/1908.01843.pdf)|BERT \\(Base\\)|0\\.7160|0\\.6710|\n|[a.soleimani.b](https://arxiv.org/pdf/1910.02655.pdf)|BERT \\(Large\\)|0\\.7186|0\\.6966 |\n|KGAT |RoBERTa \\(Large\\)|0\\.7407|0\\.7038|\n\n\nKGAT performance with different pre-trained language model.\n\n| Pre-train Model| Label Accuracy| FEVER Score |\n| --------  | -------- | -------- |\n|BERT \\(Base\\)|0\\.7281|0\\.6940|\n|BERT \\(Large\\)|0\\.7361|0\\.7024|\n|RoBERTa \\(Large\\)|0\\.7407|0\\.7038|\n|[CorefBERT](https://arxiv.org/abs/2004.06870) \\(RoBERT Large\\)|0\\.7596|0\\.7230|\n\n\n\n\n## Citation\n```\n@inproceedings{liu2020kernel,\n  title={Fine-grained Fact Verification with Kernel Graph Attention Network},\n  author={Liu, Zhenghao and Xiong, Chenyan and Sun, Maosong and Liu, Zhiyuan},\n  booktitle={Proceedings of ACL},\n  year={2020}\n}\n```\n```\n@inproceedings{liu2020adapting,\n    title = {Adapting Open Domain Fact Extraction and Verification to COVID-FACT through In-Domain Language Modeling},\n    author = {Liu, Zhenghao and Xiong, Chenyan and Dai, Zhuyun and Sun, Si and Sun, Maosong and Liu, Zhiyuan},\n    booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2020},\n   year={2020}\n}\n```\n## Contact\nIf you have questions, suggestions and bug reports, please email:\n```\nliuzhenghao0819@gmail.com\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthunlp%2Fkernelgat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthunlp%2Fkernelgat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthunlp%2Fkernelgat/lists"}