Skip to content
conftrace_
2018 EMNLP EMNLP 2018

Magnitude: A Fast, Efficient Universal Vector Embedding Utility Package

AbstractVector space embedding models like word2vec, GloVe, and fastText are extremely popular representations in natural language processing (NLP) applications. We present Magnitude, a fast, lightweight tool for utilizing and processing embeddings. Magnitude is an open source Python package with a compact vector storage file format that allows for efficient manipulation of huge numbers of embeddings. Magnitude performs common operations up to 60 to 6,000 times faster than Gensim. Magnitude introduces several novel features for improved robustness like out-of-vocabulary lookups.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - model efficiency

More from EMNLP 2018

All EMNLP 2018 papers →