glove-wiki-gigaword-100

GloVe Wikipedia + Gigaword (100 dimensions)

Pre-trained GloVe vectors for 400,000 English words, trained on Wikipedia 2014 and Gigaword 5 (6 billion tokens), uncased.

This is a gensim model, packaged for fse (Fast Sentence Embeddings), which turns word vectors into sentence vectors with CBOW averaging, SIF and uSIF.

Usage

This repository uses the fse 1.x API and requires fse<2. For fse 2.0, choose a finished encoder from the classic model catalog. See the migration guide before upgrading.

pip install "fse<2"

from fse import SIF, IndexedList, Vectors

vectors = Vectors.from_pretrained("glove-wiki-gigaword-100")
model = SIF(vectors)

sentences = IndexedList([["hello", "world"], ["fast", "sentence", "embeddings"]])
model.train(sentences)
model.sv[0]  # the vector of the first sentence

Vectors.from_pretrained("glove-wiki-gigaword-100", mmap="r") memory-maps the vectors instead of loading them into RAM.

Files

Source and license

The vectors were published by the Stanford NLP Group with GloVe under the Public Domain Dedication and License. This repository redistributes them in the gensim format.

• Pennington, Socher and Manning (2014), GloVe: Global Vectors for Word Representation

About fse

fse is maintained by Dr. Oliver Borchers. Source code, documentation and the STS benchmark of all vector sets in this organization: github.com/oborchers/Fast_Sentence_Embeddings.