StarSpace System

A StarSpace System is a embedding generation system that ...

• See: [[]].

---

---

References

2018

• http://videos.re-work.co/videos/731-learning-embeddings-at-slack
  • QUOTE: The technique of embedding discrete data in a continuous, moderate-dimensional space has proven useful for learning representations in many different domains. Embeddings learned from text, graphs, and human-created tags can support information retreival, recommendations, classification, and subjective human insight. In this talk I play with StarSpace, a new, open-source supervised embedding framework, and use it to learn representations of text, channels, and users.

2017

• https://github.com/facebookresearch/StarSpace
  • QUOTE: StarSpace is a general-purpose neural model for efficient learning of entity embeddings for solving a wide variety of problems:
    • Learning word, sentence or document level embeddings.
    • Information retrieval: ranking of sets of entities/documents or objects, e.g. ranking web documents.
    • Text classification, or any other labeling task.
    • Metric/similarity learning, e.g. learning sentence or document similarity.
    • Content-based or Collaborative filtering-based Recommendation, e.g. recommending music or videos.
    • Embedding graphs, e.g. multi-relational graphs such as Freebase.
    • Image classification, ranking or retrieval (e.g. by using existing ResNet features).
  • In the general case, it learns to represent objects of different types into a common vectorial embedding space, hence the star ('*', wildcard) and space in the name, and in that space compares them against each other. It learns to rank a set of entities/documents or objects given a query entity/document or object, which is not necessarily the same type as the items in the set.

2017

• (Wu et al., 2017) ⇒ Ledell Wu, Adam Fisch, Sumit Chopra, Keith Adams, Antoine Bordes, and Jason Weston. (2017). “StarSpace: Embed All The Things!.” In: arXiv preprint arXiv:1709.03856.
  • QUOTE: 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.

---