StarSpace: Embed All The Things!
DOI:
https://doi.org/10.1609/aaai.v32i1.11996Keywords:
Nature Language Processing, Text Classification, Knowledge Representation, Recommender SystemsAbstract
We present StarSpace, a general-purpose neural embedding model that can solve a wide variety of problems: labeling tasks such as text classification,ranking tasks such as information retrieval/web search,collaborative filtering-based or content-based recommendation,embedding of multi-relational graphs, and learning word, sentence or document level embeddings.In each case the model works by embedding those entities comprised of discrete features and comparing them against each other -- learning similarities dependent on the task.Empirical results on a number of tasks show that StarSpace is highly competitive with existing methods, whilst also being generally applicable to new cases where those methods are not.