{"id":13535226,"url":"https://github.com/nayeon7lee/bert-summarization","last_synced_at":"2025-04-02T00:32:59.018Z","repository":{"id":37593980,"uuid":"181026744","full_name":"nayeon7lee/bert-summarization","owner":"nayeon7lee","description":null,"archived":false,"fork":false,"pushed_at":"2022-12-08T04:58:34.000Z","size":53,"stargazers_count":122,"open_issues_count":17,"forks_count":32,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-11-02T23:32:43.402Z","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/nayeon7lee.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":"2019-04-12T14:41:48.000Z","updated_at":"2024-10-01T09:08:53.000Z","dependencies_parsed_at":"2023-01-24T13:00:47.795Z","dependency_job_id":null,"html_url":"https://github.com/nayeon7lee/bert-summarization","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/nayeon7lee%2Fbert-summarization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nayeon7lee%2Fbert-summarization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nayeon7lee%2Fbert-summarization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nayeon7lee%2Fbert-summarization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nayeon7lee","download_url":"https://codeload.github.com/nayeon7lee/bert-summarization/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246735357,"owners_count":20825221,"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":"2024-08-01T08:00:51.562Z","updated_at":"2025-04-02T00:32:58.676Z","avatar_url":"https://github.com/nayeon7lee.png","language":"Python","readme":"## Implementation of 'Pretraining-Based Natural Language Generation for Text Summarization'\n\nPaper: https://arxiv.org/pdf/1902.09243.pdf \n\n### Versions\n* python 2.7\n* PyTorch: 1.0.1.post2\n\n### Preparing package/dataset\n0. Run: `pip install -r requirements.txt` to install required packages\n1. Download chunk CNN/DailyMail data from: https://github.com/JafferWilson/Process-Data-of-CNN-DailyMail\n2. Run: `python news_data_reader.py` to create pickle file that will be used in my data-loader\n\n### Running the model\nFor me, the model was too big for my GPU, so I used smaller parameters as following for debugging purpose. \n`CUDA_VISIBLE_DEVICES=3 python main.py --cuda --batch_size=2 --hop 4 --hidden_dim 100`\n\n### Note to reviewer:\n* Although I implemented the core-part (2-step summary generation using BERT), I didn't have enough time to implement RL section. \n* The 2nd decoder process is very time-consuming (since it needs to create BERT context vector for each timestamp).","funding_links":[],"categories":["BERT Text Summarization Task:"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnayeon7lee%2Fbert-summarization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnayeon7lee%2Fbert-summarization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnayeon7lee%2Fbert-summarization/lists"}