Looking for Hyponyms in Vector Space

  title={Looking for Hyponyms in Vector Space},
  author={Marek Rei and Ted Briscoe},
•Dependency-based feature vectors outperformed neural network models on this task, as they were able to better capture both the context and function of words. •The vector offset method did not give an improvement, but performance could be improved by being more selective about the training examples. •Symmetric similarity measures outperformed most existing directional measures on hyponym generation. •We constructed a directional measure that achieved the best results on this task. 
Highly Cited
This paper has 41 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.

Similar Papers

Loading similar papers…