StarSpace: Embed All The Things!
Abstrak
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.
Topik & Kata Kunci
Penulis (6)
Ledell Yu Wu
Adam Fisch
S. Chopra
Keith Adams
Antoine Bordes
J. Weston
Akses Cepat
- Tahun Terbit
- 2017
- Bahasa
- en
- Total Sitasi
- 255×
- Sumber Database
- Semantic Scholar
- DOI
- 10.1609/aaai.v32i1.11996
- Akses
- Open Access ✓