Vectorized Word Representation

A Vectorized Word Representation is a text-item vector that refers to a word.

• AKA: Word-Vector, Word Embedding.
• Context:
  • It can (typically) represent a Corpus Word.
  • It can (typically) be a Contextual Word Vector, such as a distributional word vector.
  • It can be produced by a Word Vectorization Function (typically based on some text corpus)
  • It can be an input to a Word Vector-Input Function.
  • It can range from being a Weighted Word Vector to being an Unweighted Word Vector.
  • It can range from being a Sparse Word Vector to being a Dense Word Vector.
  • It can range from being a Continuous Word Vector to being a Discrete Word Vector.
  • It can be an input to an Data-Driven NLP Tasks, such as:
    • Data-Driven Syntactic Parsing (Lazaridou et al., 2013; Bansal et al., 2014).
    • Data-Driven Named Entity Recognition (Guo et al., 2014).
    • Data-Driven Sentiment Analysis (Socher et al., 2013).
• Example(s):
  • Distributional Continuous Dense Word Vector, such as: [0.128,0.208,0.008] ⇐ f("Queen")
  • Bag-of-Words Vector, such as: [0,0,1,...,0,0] ⇐ f("Queen")
  • Target-Word Context Window Vector, such as: [0,17,0,...,1,0] ⇐ f("Queen")
  • Left-Right Context Window Word Counting Tuple, such as: {targetTerm:newspaper, toTheLeft:{buys/1, this/1, every/2}, toTheRight:{day/2, read/1, a/1}}
• Counter-Example(s):
  • Phrase Vector.
  • Sentence Vector.
  • Paragraph Vector.
  • Document Vector.
  • Word Class.
• See: Lexical Semantics Model.

---

---

References

2010

• (Turney & Pantel, 2010) ⇒ Peter D. Turney, and Patrick Pantel. (2010). “From Frequency to Meaning: Vector Space Models of Semantics.” In: Journal of Artificial Intelligence Research, 37(1).

2001

• (Turney, 2001) ⇒ Peter D. Turney. (2001). “Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL.” In: Proceedings of the 12th European Conference on Machine Learning (ECML 2001)

1991

• (Miller & Charles, 1991) ⇒ G. Miller and W. Charles. (1991) "Contextual Correlates of Semantic Similarity.” In: Language and Cognitive Processes, 6(1).

---