{"id":19110156,"url":"https://github.com/zotroneneis/lstm_language_model","last_synced_at":"2025-06-23T00:04:31.850Z","repository":{"id":93478892,"uuid":"129077353","full_name":"zotroneneis/LSTM_language_model","owner":"zotroneneis","description":"LSTM-based language model in TensorFlow","archived":false,"fork":false,"pushed_at":"2020-04-02T13:47:06.000Z","size":1719,"stargazers_count":8,"open_issues_count":1,"forks_count":6,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-30T20:47:15.489Z","etag":null,"topics":["language-model","language-modeling","lstm","machine-learning","nlp","python","recurrent-neural-networks","tensorflow"],"latest_commit_sha":null,"homepage":null,"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/zotroneneis.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":"2018-04-11T10:34:32.000Z","updated_at":"2023-04-25T18:59:35.000Z","dependencies_parsed_at":null,"dependency_job_id":"525b01d1-a79e-48c3-bfd4-1fb81f5b662c","html_url":"https://github.com/zotroneneis/LSTM_language_model","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/zotroneneis/LSTM_language_model","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zotroneneis%2FLSTM_language_model","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zotroneneis%2FLSTM_language_model/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zotroneneis%2FLSTM_language_model/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zotroneneis%2FLSTM_language_model/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zotroneneis","download_url":"https://codeload.github.com/zotroneneis/LSTM_language_model/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zotroneneis%2FLSTM_language_model/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261386724,"owners_count":23150869,"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":["language-model","language-modeling","lstm","machine-learning","nlp","python","recurrent-neural-networks","tensorflow"],"created_at":"2024-11-09T04:23:53.142Z","updated_at":"2025-06-23T00:04:26.834Z","avatar_url":"https://github.com/zotroneneis.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"LSTM-based language model\n==============================\n\nThis repository contains all code and resources related to my master thesis on the topic\n\n\"Recurrent Neural Language Modeling - Using Transfer Learning to Perform Radiological Sentence Completion\"\n\nAbstract:\nMotivated by the potential benefits of a system that accelerates the process of writing radiological reports, we present a Recurrent Neural Network Language Model for modeling radiological language. We show that recurrent neural language models can be used to produce convincing radiological reports and investigate how their performance can be improved by using advanced regularization and initialization techniques. Furthermore, we study the use of transfer learning to create topic-specific language models.\n\nData\n==============================\nThe original data used in the thesis is confidential. Therefore, this repository features a version of the code that runs on the Penn Treebank dataset available [here](http:/www.fit.vutbr.cz/~imikolov/rnnlm/).\n\nTo run the code you will have to preprocess the data first. Further details on this can be found in the folder *src/data/*\n\nTestable Features\n==============================\nBy adapting the config file, the following features can be tested:\n- Variational dropout of hidden layers\n- Weight tying\n- Embedding dropout\n- Pre-trained embeddings\n\nThesis and Presentation\n==============================\nThe thesis and slides can be found in the *reports* folder \n\n\nProject Organization\n------------\n\n    ├── LICENSE\n    ├── README.md          \u003c- The top-level README \n    ├── data\n    │   ├── raw            \u003c- Original PTB files \n    │   ├── training_files \u003c- Preprocessed PTB word ids\n    │   └── embeddings     \u003c- word embeddings\n    │       │                 \n    │       ├── fasttext\n    │       └── word2vec\n    │\n    ├── models             \u003c- Trained and serialized models\n    │   ├── checkpoints    \u003c- Model checkpoints\n    │   └── tensorboard    \u003c- Tensorboard logs\n    │\n    ├── reports            \u003c- Thesis and presentation slides\n    │\n    ├── requirements.txt   \u003c- The requirements file for reproducing the analysis environment\n    │\n    ├── src                \u003c- Source code for use in this project.\n    │   │\n    │   ├── __init__.py    \u003c- Makes src a Python module\n    │   │\n    │   ├── main.py        \u003c- main file for training, testing, etc.\n    │   │\n    │   ├── config_ptb.yamp  \u003c- config file, specifying model params\n    │   │\n    │   ├── data           \u003c- scripts to preprocess data\n    │   │   │                 \n    │   │   ├── README.md\n    │   │   ├── preprocess_ptb.py\n    │   │   └── inverse_dict.py\n    │   │\n    │   ├── embeddings     \u003c- scripts to train word embeddings\n    │   │   │                 \n    │   │   ├── README.md\n    │   │   ├── fasttext.py\n    │   │   └── word2vec.py\n    │   │\n    │   ├── models         \u003c- Scripts to train models and then use trained models to make predictions\n    │   │   │                 \n    │   │   └── ptb_basic_model.py\n    │   │\n    │   └── visualization  \u003c- Scripts to create exploratory and results oriented visualizations\n    │       │                 \n    │       ├── README.md\n    │       └── visualize_embeddings.py\n    │\n    └── \n\n\n--------\n\n\u003cp\u003e\u003csmall\u003eProject based on the \u003ca target=\"_blank\" href=\"https://drivendata.github.io/cookiecutter-data-science/\"\u003ecookiecutter data science project template\u003c/a\u003e. #cookiecutterdatascience\u003c/small\u003e\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzotroneneis%2Flstm_language_model","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzotroneneis%2Flstm_language_model","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzotroneneis%2Flstm_language_model/lists"}