{"id":13540981,"url":"https://github.com/geniusai-research/email-summarization","last_synced_at":"2025-04-02T08:30:54.004Z","repository":{"id":73856197,"uuid":"143171560","full_name":"geniusai-research/email-summarization","owner":"geniusai-research","description":"A module for E-mail Summarization which uses clustering of skip-thought sentence embeddings.","archived":false,"fork":false,"pushed_at":"2018-09-21T13:20:27.000Z","size":7,"stargazers_count":82,"open_issues_count":5,"forks_count":42,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-12-31T00:04:13.829Z","etag":null,"topics":["machine-learning","skip-thought-vectors","text-summarization","theano"],"latest_commit_sha":null,"homepage":"https://medium.com/jatana/unsupervised-text-summarization-using-sentence-embeddings-adb15ce83db1","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/geniusai-research.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}},"created_at":"2018-08-01T15:02:10.000Z","updated_at":"2024-12-08T16:29:29.000Z","dependencies_parsed_at":"2024-01-16T15:45:05.410Z","dependency_job_id":"e8a1842b-a6b7-426b-9c7f-1bf65dbfdb17","html_url":"https://github.com/geniusai-research/email-summarization","commit_stats":null,"previous_names":["jatana-research/email-summarization"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/geniusai-research%2Femail-summarization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/geniusai-research%2Femail-summarization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/geniusai-research%2Femail-summarization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/geniusai-research%2Femail-summarization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/geniusai-research","download_url":"https://codeload.github.com/geniusai-research/email-summarization/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246781896,"owners_count":20832927,"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":["machine-learning","skip-thought-vectors","text-summarization","theano"],"created_at":"2024-08-01T10:00:36.946Z","updated_at":"2025-04-02T08:30:53.737Z","avatar_url":"https://github.com/geniusai-research.png","language":"Python","funding_links":[],"categories":["Papers"],"sub_categories":["Single-Document-Summarization (as references)"],"readme":"# email-summarization\nA module for E-mail Summarization which uses clustering of skip-thought sentence embeddings.\u003cbr\u003e\nThis code in this repository compliments [this Medium article](https://medium.com/jatana/unsupervised-text-summarization-using-sentence-embeddings-adb15ce83db1).\n## Instructions\n- The code is written in Python 2. \n- The module uses code of the [Skip-Thoughts paper](http://arxiv.org/abs/1506.06726) which can be found [here](https://github.com/ryankiros/skip-thoughts). Do:\n  ```\n  git clone https://github.com/ryankiros/skip-thoughts\n  ```\n- The code for the skip-thoughts paper uses [Theano](http://deeplearning.net/software/theano/install.html). Make sure you have Theano installed and GPU acceleration is functional for faster execution. \n- Clone this repository and copy the file `email_summarization.py` to the root of the cloned skip-thoughts repository. Do:\n  ```\n  git clone https://github.com/jatana-research/email-summarization\n  cp email-summarization/email_summarization.py skip-thoughts/\n  ```\n- Install dependencies. Do:\n  ```\n  pip install -r email-summarization/requirements.txt\n  python -c 'import nltk; nltk.download(\"punkt\")'\n  ```\n- Download the pre-trained models. The total download size will be of around 5 GB. Do:\n  ```\n  mkdir skip-thoughts/models\n  wget -P ./skip-thoughts/models http://www.cs.toronto.edu/~rkiros/models/dictionary.txt\n  wget -P ./skip-thoughts/models http://www.cs.toronto.edu/~rkiros/models/utable.npy\n  wget -P ./skip-thoughts/models http://www.cs.toronto.edu/~rkiros/models/btable.npy\n  wget -P ./skip-thoughts/models http://www.cs.toronto.edu/~rkiros/models/uni_skip.npz\n  wget -P ./skip-thoughts/models http://www.cs.toronto.edu/~rkiros/models/uni_skip.npz.pkl\n  wget -P ./skip-thoughts/models http://www.cs.toronto.edu/~rkiros/models/bi_skip.npz\n  wget -P ./skip-thoughts/models http://www.cs.toronto.edu/~rkiros/models/bi_skip.npz.pkl\n  ``` \n- Verify the MD5 hashes of the downloaded files to ensure that the files haven't been corrupted during the download. Do:\n  ```\n  md5sum skip-thoughts/models/*\n  ```\n  The output should be:\n  ```\n  9a15429d694a0e035f9ee1efcb1406f3 bi_skip.npz\n  c9b86840e1dedb05837735d8bf94cee2 bi_skip.npz.pkl\n  022b5b15f53a84c785e3153a2c383df6 btable.npy\n  26d8a3e6458500013723b380a4b4b55e dictionary.txt\n  8eb7c6948001740c3111d71a2fa446c1 uni_skip.npz\n  e1a0ead377877ff3ea5388bb11cfe8d7 uni_skip.npz.pkl\n  5871cc62fc01b79788c79c219b175617 utable.npy\n  ```\n- Change `Lines:23-24` in the file `skip-thoughts/skipthoughts.py` to provide the correct paths to the downloaded models.\n  ```\n  path_to_models = 'models/'\n  path_to_tables = 'models/'\n  ```\n  \n## Running the module\n- Find any English emails dataset online or create a small one on your own.\n- The module expects a list of emails as input and returns a list of summaries.\n- Open the Python interpreter in the `skip-thoughts/` folder and do:\n  ```\n  \u003e\u003e\u003e from email_summarization import summarize\n  \u003e\u003e\u003e summaries = summarize(emails) # emails is a Python list containing English emails.\n  ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgeniusai-research%2Femail-summarization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgeniusai-research%2Femail-summarization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgeniusai-research%2Femail-summarization/lists"}