word2vec Vector

A word2vec Vector is a continuous dense distributional word vector produced by a word2vec model.

• Context:
  • It can (typically) be a member of a word2vec Model Vector Space.
• Example(s):
  • the vector for the term 'shortly afterwards' from the model created by v1 code on the 20 Newsgroups Corpus using settings -cbow 1 -negative 25 -hs 0 -sample 1e-4 -threads 40 -binary 1 -iter 15 -window 8 -size 200.
  • Toshiba -1.806884 0.264727 0.559126 -0.731248 1.536955 0.721408 1.262543 -1.319138 1.539470 -0.555704 2.753093 -1.744820 3.653871 2.710065 -1.342534 2.741013 -0.286641 -1.071824 0.414057 2.587884 -2.478674 2.385714 0.994736 2.393804 0.639196 -1.795311 1.378787 -1.653974 -2.459703
• Counter-Example(s):
  • a Dependency Parse-based Vector.
  • a Window Baseline-based Vector.
• See: word2vec Distance Function, word2vec Analogy Function.

---

---

References

2013

• (Rei & Briscoe, 2014) ⇒ Marek Rei, and Ted Briscoe. (2014). “Looking for Hyponyms in Vector Space.” In: Proceedings of CoNLL-2014.
  • QUOTE: The window-based, dependency-based and word2vec vector sets were all trained on 112M words from the British National Corpus, with preprocessing steps for lower-casing and lemmatising. Any numbers were grouped and substituted by more generic tokens.

---