Word Representations: A Simple and General Method for Semi-Supervised Learning

@inproceedings{Turian2010WordRA,
  title={Word Representations: A Simple and General Method for Semi-Supervised Learning},
  author={Joseph P. Turian and Lev-Arie Ratinov and Yoshua Bengio},
  booktitle={ACL},
  year={2010}
}
If we take an existing supervised NLP system, a simple and general way to improve accuracy is to use unsupervised word representations as extra word features. We evaluate Brown clusters, Collobert and Weston (2008) embeddings, and HLBL (Mnih & Hinton, 2009) embeddings of words on both NER and chunking. We use near state-of-the-art supervised baselines, and find that each of the three word representations improves the accuracy of these baselines. We find further improvements by combining… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 1,451 CITATIONS

Radical-Enhanced Chinese Character Embedding

  • ICONIP
  • 2014
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Biased Representation Learning for Domain Adaptation

  • EMNLP-CoNLL
  • 2012
VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Training Restricted Boltzmann Machines on Word Observations

VIEW 20 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2009
2019

CITATION STATISTICS

  • 179 Highly Influenced Citations

  • Averaged 173 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 51 REFERENCES

Semi-supervised learning for natural language

P. Liang
  • Master’s thesis, Massachusetts Institute of Technology.
  • 2005
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Neural net language models

  • Scholarpedia
  • 2008
VIEW 8 EXCERPTS

Dimensionality reduction by random mapping: fast similarity computation for clustering

  • 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227)
  • 1998
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL