ThoughtRiver / lmdb-embeddingsLinks
Fast word vectors with little memory usage in Python
☆416Updated 4 years ago
Alternatives and similar repositories for lmdb-embeddings
Users that are interested in lmdb-embeddings are comparing it to the libraries listed below
Sorting:
- A context-preserving word cloud generator☆443Updated 2 years ago
- All-pair set similarity search on millions of sets in Python and on a laptop☆597Updated 2 years ago
- Scikit-learn style model finetuning for NLP☆711Updated this week
- Quantized word vectors that take 8x-16x less space than regular word vectors☆752Updated 5 years ago
- Intuitive Annotation Tool for Information Extraction / Named Entity Recognition using localturk / Amazon Mechanical Turk☆265Updated 5 years ago
- Efficient Counter that uses a limited (bounded) amount of memory regardless of data size.☆933Updated 2 years ago
- scikit-learn wrappers for Python fastText.☆232Updated 3 years ago
- Calculates Word Mover's Distance Insanely Fast☆461Updated last year
- Feature engineering and machine learning: together at last!☆24Updated 4 years ago
- A high-level, rapid development framework for machine learning projects☆344Updated last year
- Organized Resources for Deep Learning in Natural Language Processing☆435Updated 5 years ago
- A fast, efficient universal vector embedding utility package.☆1,649Updated last year
- Lazydata: Scalable data dependencies for Python projects☆621Updated 6 years ago
- Dynamic Meta-Embeddings for Improved Sentence Representations☆332Updated 4 years ago
- 🚀100 Times Faster Natural Language Processing in Python - iPython notebook☆338Updated 7 years ago
- Textpipe: clean and extract metadata from text☆302Updated 4 years ago
- Unsupervised Language Modeling at scale for robust sentiment classification☆1,063Updated 5 years ago
- Bidirectionally transformed strings☆367Updated last year
- Text Classification Library in Keras☆420Updated 7 years ago
- Yet another Python binding for fastText☆224Updated 6 years ago
- Various Algorithms for Short Text Mining☆471Updated last week
- A multi-model machine learning feature embedding database☆638Updated 5 years ago
- Multilingual word vectors in 78 languages☆1,199Updated 2 years ago
- Exploring word2vec embeddings as a graph of nearest neighbors☆710Updated 4 years ago
- 💫 REST microservices for various spaCy-related tasks☆240Updated 3 years ago
- tensorflow port of the lda2vec model for unsupervised learning of document + topic + word embeddings☆436Updated 8 years ago
- Code for the paper "DeepType: Multilingual Entity Linking by Neural Type System Evolution"☆650Updated 2 years ago
- 💫 Scripts, tools and resources for developing spaCy☆126Updated 6 years ago
- Generating labels for topics automatically using neural embeddings☆185Updated 4 months ago
- A knowledge base construction engine for richly formatted data☆410Updated 4 years ago