@InProceedings{nguyen-EtAl:2017:EMNLP2017,
  author    = {Nguyen, Kim Anh  and  K\"{o}per, Maximilian  and  Schulte im Walde, Sabine  and  Vu, Ngoc Thang},
  title     = {Hierarchical Embeddings for Hypernymy Detection and Directionality},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {233--243},
  abstract  = {We present a novel neural model HyperVec to learn hierarchical embeddings for
	hypernymy detection and directionality. While previous embeddings have shown
	limitations on prototypical hypernyms, HyperVec represents an unsupervised
	measure where embeddings are learned in a specific order and capture the
	hypernym--hyponym distributional hierarchy. Moreover, our model is able to
	generalize over unseen hypernymy pairs, when using only small sets of training
	data, and by mapping to other languages. Results on benchmark datasets show
	that HyperVec outperforms both state-of-the- art unsupervised measures and
	embedding models on hypernymy detection and directionality, and on predicting
	graded lexical entailment.},
  url       = {https://www.aclweb.org/anthology/D17-1022}
}