{"id":13753285,"url":"https://github.com/steph1793/Pointer_Transformer_Generator","last_synced_at":"2025-05-09T20:35:13.554Z","repository":{"id":127476409,"uuid":"202012541","full_name":"steph1793/Pointer_Transformer_Generator","owner":"steph1793","description":":scorpius::heavy_plus_sign::sagittarius::arrow_right::heavy_check_mark: Build a summarizer models combining transformers and pointing mechanism","archived":false,"fork":false,"pushed_at":"2019-11-28T21:07:37.000Z","size":66,"stargazers_count":34,"open_issues_count":6,"forks_count":7,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-16T05:32:40.866Z","etag":null,"topics":[],"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/steph1793.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-08-12T21:35:01.000Z","updated_at":"2023-07-23T10:14:34.000Z","dependencies_parsed_at":null,"dependency_job_id":"f5d808e3-6a59-4009-b76c-62307deef6eb","html_url":"https://github.com/steph1793/Pointer_Transformer_Generator","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/steph1793%2FPointer_Transformer_Generator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/steph1793%2FPointer_Transformer_Generator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/steph1793%2FPointer_Transformer_Generator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/steph1793%2FPointer_Transformer_Generator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/steph1793","download_url":"https://codeload.github.com/steph1793/Pointer_Transformer_Generator/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253321858,"owners_count":21890480,"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":"2024-08-03T09:01:19.608Z","updated_at":"2025-05-09T20:35:08.517Z","avatar_url":"https://github.com/steph1793.png","language":"Python","funding_links":[],"categories":["文本摘要"],"sub_categories":[],"readme":"# Pointer_Transformer_Generator tensorflow 2.0.0\n\nFor the abstractive summarization task, I wanted to experiment the transformer model. I recreated a transformer model (thanks to tensorflow transformer tutorial) and added a pointer module (have a look at this paper for more informations on the pointer generator network : https://arxiv.org/abs/1704.04368 ).\n\nPS : I will add very soon a section explaining the integration of the pointer module in the transformer\n\nPlease follow the next steps to launch the project :\n\n## Step 1 : The data\n\n### Option 1 : Download the data\nDownload the data (chunk files format : tfrecords)\nhttps://drive.google.com/open?id=1uHrMWd7Pbs_-DCl0eeMxePbxgmSce5LO\n\n### Option 2 : Download raw data and process it\nUse this project : \nhttps://github.com/steph1793/CNN-DailyMail-Bin-To-TFRecords\n\n## Step 2 : launch the project : \n\n**python main.py --max_enc_len=400 \\ \u003cbr\u003e\n--max_dec_len=100 \\ \u003cbr\u003e\n--batch_size=16 \\ \u003cbr\u003e\n--vocab_size=50000 \\ \u003cbr\u003e\n--num_layers=3 \\ \u003cbr\u003e\n--model_depth=512 \\ \u003cbr\u003e\n--num_heads=8 \\ \u003cbr\u003e\n--dff=2048 \\ \u003cbr\u003e\n--seed=123 \\ \u003cbr\u003e\n--log_step_count_steps=1 \\ \u003cbr\u003e\n--max_steps=230000 \\ \u003cbr\u003e\n--mode=train \\ \u003cbr\u003e\n--save_summary_steps=10000 \\ \u003cbr\u003e\n--checkpoints_save_steps=10000 \\ \u003cbr\u003e\n--model_dir=model_folder \\ \u003cbr\u003e\n--data_dir=data_folder \\ \u003cbr\u003e\n--vocab_path=vocab \\ \u003cbr\u003e**\n\nPS : Feel free to change some of the hyperparameters\u003cbr\u003e\npython main.py --help , for more details on the hyperparameters\n\n\n\n## Requirements\n- python \u003e= 3.6\n- tensorflow 2.0.0\n- argparse\n- os\n- glob\n- numpy\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsteph1793%2FPointer_Transformer_Generator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsteph1793%2FPointer_Transformer_Generator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsteph1793%2FPointer_Transformer_Generator/lists"}