StarSpace: Embed All the Things!

Ledell Yu Wu, Adam Fisch, Sumit Chopra, Keith Adams, Antoine Bordes, Jason Weston

AAAI 2018 pp. 5569-5577

doi:10.1609/AAAI.V32I1.11996 /aaai/2018/wu2018aaai-starspace/

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.

PDF AAAI Semantic Scholar

Cite

Text

Wu et al. "StarSpace: Embed All the Things!." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.11996

Markdown

[Wu et al. "StarSpace: Embed All the Things!." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/wu2018aaai-starspace/) doi:10.1609/AAAI.V32I1.11996

BibTeX

@inproceedings{wu2018aaai-starspace,
  title     = {{StarSpace: Embed All the Things!}},
  author    = {Wu, Ledell Yu and Fisch, Adam and Chopra, Sumit and Adams, Keith and Bordes, Antoine and Weston, Jason},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {5569-5577},
  doi       = {10.1609/AAAI.V32I1.11996},
  url       = {https://mlanthology.org/aaai/2018/wu2018aaai-starspace/}
}