Low-Dimensional Dense Vector Space

A Low-Dimensional Dense Vector Space is a dense vector space that is a low-dimensional space.

• Context:
  • It can (typically) have fewer than 300 dimensions.
  • It can be associated to a Low-Dimensional Dense Vector Space Function (created by a low-dimensional dense vector space function fitting task).
• Example(s):
  • one created by a word2vec to represent a word space.
  • …
• Counter-Example(s):
  • High-Dimensional Vector Space.
• See: Vector Space.

---

---

References

2015

• (Rothe & Schütze, 2015) ⇒ Sascha Rothe, and Hinrich Schütze. (2015). “AutoExtend: Extending Word Embeddings to Embeddings for Synsets and Lexemes.” In: arXiv preprint arXiv:1507.01127.
  • QUOTE: We present AutoExtend, a system to learn embeddings for synsets and lexemes. |It is flexible in that it can take any word embeddings as input and does not need an additional training corpus. The synset/lexeme embeddings obtained live in the same vector space as the word embeddings. …

    .... Unsupervised methods for word embeddings (also called “distributed word representations”) have become popular in natural language processing (NLP). These methods only need very large corpora as input to create sparse representations (e.g., based on local collocations) and project them into a lower dimensional dense vector space. Examples for word embeddings are SENNA (Collobert and Weston, 2008), the hierarchical log-bilinear model (Mnih and Hinton, 2009), word2vec (Mikolov et al., 2013c) and GloVe (Pennington et al., 2014).

---