{"id":13709667,"url":"https://github.com/lixinsu/RCZoo","last_synced_at":"2025-05-06T16:32:11.725Z","repository":{"id":70881868,"uuid":"142098127","full_name":"lixinsu/RCZoo","owner":"lixinsu","description":"question answering, reading comprehension toolkit","archived":false,"fork":false,"pushed_at":"2022-10-16T05:37:21.000Z","size":13357,"stargazers_count":167,"open_issues_count":12,"forks_count":43,"subscribers_count":15,"default_branch":"master","last_synced_at":"2024-11-13T19:40:42.218Z","etag":null,"topics":["deep-learning","question-answering","reading-comprehension"],"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/lixinsu.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":"2018-07-24T03:14:18.000Z","updated_at":"2024-09-05T08:27:48.000Z","dependencies_parsed_at":"2023-06-13T03:00:08.588Z","dependency_job_id":null,"html_url":"https://github.com/lixinsu/RCZoo","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/lixinsu%2FRCZoo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lixinsu%2FRCZoo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lixinsu%2FRCZoo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lixinsu%2FRCZoo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lixinsu","download_url":"https://codeload.github.com/lixinsu/RCZoo/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252721082,"owners_count":21793748,"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":["deep-learning","question-answering","reading-comprehension"],"created_at":"2024-08-02T23:00:43.543Z","updated_at":"2025-05-06T16:32:10.971Z","avatar_url":"https://github.com/lixinsu.png","language":"Python","funding_links":[],"categories":["Repository \u0026 Toolkit"],"sub_categories":[],"readme":"\n## Introduction\nThe RCZoo project is a toolkit for reading comprehension model. It contains the [PyTorch](https://pytorch.org/) reimplement of multiple reading comprehension models  \n\n## Usage\n - run `sh download.sh` to download the dataset and the glove embeddings. \n - run `sh runs/train_squad.sh [bidaf|drqa|slqa|fusionnet|docqa]` to start the train process. (Check the xxx.sh scripts before run, as the preprocessing only need to be executed once)\n\n \n## Dependencies\npython 3.5  \nPytorch 0.4  \ntqdm  \n\n\n## performance\n\nWe train each model on train set for 40 epoch, and report the best performance on dev set.  \n\nModel | Exact Match | F1 | EM(+ELMo) | F1(+ELMo)\n---- | --- | --- | --- | --- \nRnet | 69.25 | 78.97 |\nBiDAF | 70.47 | 79.90 | 73.04 | 81.48\ndocumentqa | 71.47 | 80.84 | \nDrQA | 68.39 | 77.90 |\nQAnet | ... | ... |\nSLQA | 67.09 | 76.67 | \nFusionNet | 68.27 | 77.79 |  \n\n## Current progress\n### [Rnet](https://www.microsoft.com/en-us/research/wp-content/uploads/2017/05/r-net.pdf)\n### [BiDAF](https://arxiv.org/abs/1611.01603)\n### [documentqa](https://arxiv.org/abs/1710.10723)\n### [DrQA](https://arxiv.org/abs/1704.00051)\n### [QAnet](https://arxiv.org/abs/1804.09541)\n### [SLQA](http://aclweb.org/anthology/P18-1158)\n### [FusionNet](https://openreview.net/forum?id=BJIgi_eCZ\u0026noteId=BJIgi_eCZ)\n\n ## acknowledgement\n some code are borrowed from [DrQA](https://github.com/facebookresearch/DrQA.git), a cool project about reading comprehension.  \n \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flixinsu%2FRCZoo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flixinsu%2FRCZoo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flixinsu%2FRCZoo/lists"}