English

Word Embeddings: A Survey

Computation and Language 2023-05-03 v2 Machine Learning Machine Learning

Abstract

This work lists and describes the main recent strategies for building fixed-length, dense and distributed representations for words, based on the distributional hypothesis. These representations are now commonly called word embeddings and, in addition to encoding surprisingly good syntactic and semantic information, have been proven useful as extra features in many downstream NLP tasks.

Keywords

Cite

@article{arxiv.1901.09069,
  title  = {Word Embeddings: A Survey},
  author = {Felipe Almeida and Geraldo Xexéo},
  journal= {arXiv preprint arXiv:1901.09069},
  year   = {2023}
}

Comments

10 pages, 2 tables, 1 image This version, fixed a typo just before section 3.1

R2 v1 2026-06-23T07:22:39.461Z