Abstract | ||
---|---|---|
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. |
Year | Venue | DocType |
---|---|---|
2018 | national conference on artificial intelligence | Conference |
Volume | Citations | PageRank |
abs/1709.03856 | 18 | 0.65 |
References | Authors | |
14 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ledell Yu Wu | 1 | 21 | 1.04 |
Adam Fisch | 2 | 18 | 0.65 |
Sumit Chopra | 3 | 2835 | 181.37 |
Keith Adams | 4 | 41 | 1.73 |
Antoine Bordes | 5 | 3289 | 157.12 |
Jason Weston | 6 | 13068 | 805.30 |