{"id":20435481,"url":"https://github.com/jacksonchen1998/multi-turn-dialogue-response","last_synced_at":"2025-04-12T21:33:56.936Z","repository":{"id":252910278,"uuid":"805419527","full_name":"jacksonchen1998/Multi-turn-Dialogue-Response","owner":"jacksonchen1998","description":"Master Thesis","archived":false,"fork":false,"pushed_at":"2024-08-13T09:01:17.000Z","size":306,"stargazers_count":20,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-03-26T15:48:03.928Z","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/jacksonchen1998.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":"2024-05-24T14:31:15.000Z","updated_at":"2024-10-24T08:18:35.000Z","dependencies_parsed_at":null,"dependency_job_id":"59c234dc-ef46-413a-8243-d5193c6ee923","html_url":"https://github.com/jacksonchen1998/Multi-turn-Dialogue-Response","commit_stats":null,"previous_names":["jacksonchen1998/multi-turn-dialogue-response"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacksonchen1998%2FMulti-turn-Dialogue-Response","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacksonchen1998%2FMulti-turn-Dialogue-Response/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacksonchen1998%2FMulti-turn-Dialogue-Response/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jacksonchen1998%2FMulti-turn-Dialogue-Response/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jacksonchen1998","download_url":"https://codeload.github.com/jacksonchen1998/Multi-turn-Dialogue-Response/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248636844,"owners_count":21137527,"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":"2024-11-15T08:34:44.486Z","updated_at":"2025-04-12T21:33:56.929Z","avatar_url":"https://github.com/jacksonchen1998.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Multi-turn-Dialogue-Response\n\n![image](fig/kitm.png)\n\n## Install requirements.txt\n\n```bash\nconda install --yes --file requirements.txt\n```\n\n## Pre-processing\n\n* Download  [**Pretrained GloVe Embeddings**](http://nlp.stanford.edu/data/glove.6B.zip) and save it in `/vectors`.\n* The preprocessed dataset is saved as `/data/ED/dataset_preproc.p`. If you want to create the dataset yourself or change the knowledge types generated by COMET, delete this file, download the [COMET checkpoint](https://github.com/allenai/comet-atomic-2020) and place it in `/data/ED/Comet`. The preprocessed dataset would be generated after the training script. Here, we use BART, since the GPT-2 version can not be used.\n\n## Dataset\n\nIn this study we use two different dataset. In this repository, we set the config and mapping to EmpatheticDialogues.\n\n- [EmpatheticDialogues](https://github.com/facebookresearch/EmpatheticDialogues)\n- [DailyDialog](http://yanran.li/dailydialog)\n\n### Data Resource\n\n- [EmpatheticDialogues](https://drive.google.com/drive/folders/1UiEr4ug0nc4uJQYvvO2U4MHt3bhf66VW?usp=sharing)\n- [DailyDialog](https://drive.google.com/drive/folders/1nUBCQjNjlNjqLZykrYoiKxDAKUVYQApK?usp=sharing)\n\n### Data Structure\n\nThe `data` folder is organized as follows:\n\n```\ndata\n|--- ED\n|    |--- Comet\n|    |--- emp.pkl\n|    |--- train.csv\n|    |--- valid.csv\n|    |--- test.csv\n|    \n|--- DD\n|    |--- Comet\n|    |--- dd.pkl\n|    |--- train.csv\n|    |--- valid.csv\n|    |--- test.csv\n```\n\n### Directory and File Descriptions\n\n- **`data/`**: The root directory containing all data files.\n\n  - **`ED/`**: This directory contains files for the \"EmpatheticDialogues\" dataset.\n  \n    - **`Comet/`**: A subdirectory containing the \"Comet\" package used to generate common-sense knowledge.\n    \n    - **`emp.pkl`**: A pickle file containing topic appearance probabilities for the \"EmpatheticDialogues\" dataset.\n    \n    - **`train.csv`**: The training data file for the \"EmpatheticDialogues\" dataset.\n    \n    - **`valid.csv`**: The validation data file for the \"EmpatheticDialogues\" dataset.\n    \n    - **`test.csv`**: The testing data file for the \"EmpatheticDialogues\" dataset.\n    \n  - **`DD/`**: This directory contains files for the \"DailyDialog\" dataset.\n  \n    - **`Comet/`**: A subdirectory containing the \"Comet\" package used to generate common-sense knowledge.\n    \n    - **`dd.pkl`**: A pickle file containing topic appearance probabilities for the \"DailyDialog\" dataset.\n    \n    - **`train.csv`**: The training data file for the \"DailyDialog\" dataset.\n    \n    - **`valid.csv`**: The validation data file for the \"DailyDialog\" dataset.\n    \n    - **`test.csv`**: The testing data file for the \"DailyDialog\" dataset.\n\n## Training\n\n```bash\npython main.py --cuda --save_path save/your_dir\n```\n\n## Testing\n\n```bash\npython main.py --cuda --test --save_path save/your_dir --model_path save/dir_save/KITM_XXXX.XXX\n```\n\nPlease be free to contact with us via present90308.ee11@nycu.edu.tw\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacksonchen1998%2Fmulti-turn-dialogue-response","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjacksonchen1998%2Fmulti-turn-dialogue-response","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjacksonchen1998%2Fmulti-turn-dialogue-response/lists"}