Learn Text 'Embeddings' with 'Starspace'
Cosine and Inner product based similarity
Predict using a Starspace model
Get the scale of embedding similarities alongside a Starspace model
Interface to Starspace for training a Starspace model
Get the dictionary of a Starspace model
Get the document or ngram embeddings
K-nearest neighbours using a Starspace model
Load a Starspace model
Build a Starspace model for learning the mapping between sentences and...
Build a Starspace model for content-based recommendation
Build a Starspace model for entity relationship completion
Build a Starspace model for interest-based recommendation
Build a Starspace model to be used for sentence embedding
Build a Starspace model to be used for classification purposes
Build a Starspace model which calculates word embeddings
Save a starspace model as a binary or tab-delimited TSV file
Wraps the 'StarSpace' library <https://github.com/facebookresearch/StarSpace> allowing users to calculate word, sentence, article, document, webpage, link and entity 'embeddings'. By using the 'embeddings', you can perform text based multi-label classification, find similarities between texts and categories, do collaborative-filtering based recommendation as well as content-based recommendation, find out relations between entities, calculate graph 'embeddings' as well as perform semi-supervised learning and multi-task learning on plain text. The techniques are explained in detail in the paper: 'StarSpace: Embed All The Things!' by Wu et al. (2017), available at <arXiv:1709.03856>.