Distributional Vector

A Distributional Vector is a vector that represents an item based on its context within a large dataset.

• Context:
  • It can be seen as a numerical representation of a word or item that reflects its contextual usage.
  • It can be generated based on the frequency or co-occurrence of words/items in proximity to the target word/item in a given corpus or dataset.
  • …
• Example(s):
  • Word2Vec Vector.
  • TF-IDF Vector (Term Frequency-Inverse Document Frequency) vectors in document retrieval.
  • Topic Modeling Vector generated from the distribution of topics across documents.
  • Customer Segmentation Vector that represent customer behavior based on purchase history.
  • Genomic Vectors representing the context of a particular gene within a genome.
  • Embedding Space Vector.
  • …
• Counter-Example(s):
  • One-hot Vectors: These vectors represent a word or item without any contextual information.
• See: Embedding Space, Co-Occurrence Word Vector, Distributional Model, Distributional Continuous Word Vector.

---

---