├── .gitignore ├── LICENSE ├── README.md ├── config ├── glove_sample_config.yml ├── lsa_sample_config.yml └── word2vec_sample_config.yml ├── data ├── fake_data.txt └── text8.zip ├── main.py ├── matrix ├── PIP_loss_calculator.py ├── __init__.py ├── glove_matrix.py ├── ppmi_lsa_matrix.py ├── signal_matrix.py ├── signal_matrix_factory.py └── word2vec_matrix.py ├── requirements.txt ├── test ├── __init__.py └── test_tokenizer.py └── utils ├── __init__.py ├── reader.py └── tokenizer.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc 2 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/README.md -------------------------------------------------------------------------------- /config/glove_sample_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/config/glove_sample_config.yml -------------------------------------------------------------------------------- /config/lsa_sample_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/config/lsa_sample_config.yml -------------------------------------------------------------------------------- /config/word2vec_sample_config.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/config/word2vec_sample_config.yml -------------------------------------------------------------------------------- /data/fake_data.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/data/fake_data.txt -------------------------------------------------------------------------------- /data/text8.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/data/text8.zip -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/main.py -------------------------------------------------------------------------------- /matrix/PIP_loss_calculator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/matrix/PIP_loss_calculator.py -------------------------------------------------------------------------------- /matrix/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /matrix/glove_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/matrix/glove_matrix.py -------------------------------------------------------------------------------- /matrix/ppmi_lsa_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/matrix/ppmi_lsa_matrix.py -------------------------------------------------------------------------------- /matrix/signal_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/matrix/signal_matrix.py -------------------------------------------------------------------------------- /matrix/signal_matrix_factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/matrix/signal_matrix_factory.py -------------------------------------------------------------------------------- /matrix/word2vec_matrix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/matrix/word2vec_matrix.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/requirements.txt -------------------------------------------------------------------------------- /test/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /test/test_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/test/test_tokenizer.py -------------------------------------------------------------------------------- /utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /utils/reader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/utils/reader.py -------------------------------------------------------------------------------- /utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ziyin-dl/word-embedding-dimensionality-selection/HEAD/utils/tokenizer.py --------------------------------------------------------------------------------