Word Vectorizing Function

A Word Vectorizing Function is a vector space mapping function that maps a word into a word vector space model.

• AKA: Term Vectorization Function, Word to Word Vector Mapping Structure.
• Context:
  • It can be produced by a Word Vector Space Model Creation Task/Word Vectorizing Function Creation Task (that often accepts a corpus).
• Example(s):
  • [math]\displaystyle{ f(\text{The United Nations})\rightarrow (-1.29177,1.27297,...,0.30471) }[/math]
  • a word2vec Word Mapping Function.
  • …
• Counter-Example(s):
  • a Sentence Vectorizing Function.
  • a Word Classification Function.
  • a Document Vectorizing Function.
  • a Word Vector-Input Function.
  • an Image Vector Space Mapping Function.
• See: Text-Item Vectorization Function, Vector Distance Function, Text Item, Semantic Mapping Function.

---

---

References

2015

• (Vilnis & McCallum, 2015) ⇒ Luke Vilnis, and Andrew McCallum. (2015). “Word Representations via Gaussian Embedding.” In: arXiv preprint arXiv:1412.6623 submitted to ICRL 2015.
  • QUOTE: ... interest in learning compact distributed representations or embeddings for many machine learning tasks, including collaborative filtering (Koren et al., 2009), image retrieval (Weston et al., 2011), relation extraction (Riedel et al., 2013), word semantics and language modeling (Bengio et al., 2006; Mnih & Hinton, 2008; Mikolov et al., 2013), and many others. In these approaches input objects (such as images, relations or words) are mapped to dense vectors having lower-dimensionality than the cardinality of the inputs, with the goal that the geometry of his low-dimensional latent embedded space be smooth with respect to some measure of similarity in the target domain.

---