Word Vector Space

A Word Vector Space is a vector space composed of word vectors.

• AKA: Lexical Item Vector Model, Token Feature Space.
• Context:
  • It can be (typically) defined by a Word Vector Space Model (based on some corpus statistics).
  • It can range from being a Binary Word Vector Space, to being a Non-Negative Integer Word Vector Space to being a Continuous Word Vector Space.
  • It can be produced by a Word Vector Space Creation Task (solved by a Word Vector Space Creation System)
• Example(s):
  • the vector space associated with the 20 Newsgroups Dataset.
  • …
• Counter-Example(s):
  • a DNA Vector Space.
• See: Bag-of-Words Vector Space.

---

---

References

2013

• https://code.google.com/p/word2vec/
  • This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently used in many natural language processing applications and for further research.

---