Inproceedings,

Efficient Estimation of Word Representations in Vector Space

, , , and .
Proceedings of the First International Conference on Learning Representations, (2013)

Abstract

We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a word similarity task, and the results are compared to the previously best performing techniques based on different types of neural networks. We observe large improvements in accuracy at much lower computational cost, i.e. it takes less than a day to learn high quality word vectors from a 1.6 billion words data set. Furthermore, we show that these vectors provide state-of-the-art performance on our test set for measuring syntactic and semantic word similarities.

Tags

Users

  • @wool
  • @ghagerer
  • @thoni
  • @scheuerpflug
  • @albinzehe
  • @annakrause
  • @stdiff
  • @nosebrain
  • @dblp
  • @timuw
  • @sxkdz
  • @habereder
  • @florianpircher
  • @ven7u
  • @wangxinxi
  • @bechr7
  • @tobias.koopmann
  • @michan
  • @hauptmann
  • @tschumacher
  • @mcreinhardt
  • @festplatte

Comments and Reviewsshow / hide

  • @michan
    @michan 3 years ago
    Diese Paper stellt Word2Vec vor, eine Methode die genannt wird um den Vorteil von Transformer Modellen aufzuzeigen.
  • @timuw
    @timuw 4 years ago
    Dieses Paper bildet die Grundlage auf der DeepWalk aufbaut. Die vorgestellte Methode wird auf Graphen angewandt.
Please log in to take part in the discussion (add own reviews or comments).