GloVe is an unsupervised learning algorithm for obtaining vector representations for words. Training is performed on aggregated global word-word co-occurrence statistics from a corpus, and the resulting representations showcase interesting linear substructures of the word vector space. The links provided contain word vectors obtained from the respective corpora. If you want word vectors trained on massive web datasets, you need only download one of these text files! Pre-trained word vectors are made available under the Public Domain Dedication and License. If the web datasets above don't match the semantics of your end use case, you can train word vectors on your own corpus. The demo.sh script downloads a small corpus, consisting of the first 100M characters of Wikipedia. It collects unigram counts, constructs and shuffles cooccurrence data, and trains a simple version of the GloVe model. It also runs a word analogy evaluation script in python to verify word vector quality.
Features
- Global vectors for word representation
- Available pre-trained word vectors
- The GloVe model is trained on the non-zero entries of a global word-word co-occurrence matrix
- The tools provided in this package automate the collection and preparation of co-occurrence statistics for input into the model
- GloVe is essentially a log-bilinear model with a weighted least-squares objective
- The training objective of GloVe is to learn word vectors such that their dot product equals the logarithm of the words' probability of co-occurrence
Project Samples
