Evaluation methods for unsupervised word embeddings

@inproceedings{Schnabel2015EvaluationMF,
  title={Evaluation methods for unsupervised word embeddings},
  author={Tobias Schnabel and Igor Labutov and David M. Mimno and Thorsten Joachims},
  booktitle={EMNLP},
  year={2015}
}
We present a comprehensive study of evaluation methods for unsupervised embedding techniques that obtain meaningful representations of words from text. Different evaluations result in different orderings of embedding methods, calling into question the common assumption that there is one single optimal vector representation. We present new evaluation techniques that directly compare embeddings with respect to specific queries. These methods reduce bias, provide greater insight, and allow us to… CONTINUE READING
Highly Influential
This paper has highly influenced 20 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 174 citations. REVIEW CITATIONS
127 Citations
29 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 127 extracted citations

174 Citations

0204060802015201620172018
Citations per Year
Semantic Scholar estimates that this publication has 174 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 29 references

Similar Papers

Loading similar papers…