@InProceedings{nakashole-flauger:2017:EMNLP2017,
  author    = {Nakashole, Ndapandula  and  Flauger, Raphael},
  title     = {Knowledge Distillation for Bilingual Dictionary Induction},
  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     = {2497--2506},
  abstract  = {Leveraging zero-shot learning to learn
	mapping functions between vector spaces
	of different languages is a promising approach
	to bilingual dictionary induction.
	However, methods using this approach
	have not yet achieved high accuracy on the
	task. In this paper, we propose a bridging
	approach, where our main contribution
	is a knowledge distillation training objective.
	As teachers, rich resource translation
	paths are exploited in this role. And
	as learners, translation paths involving low
	resource languages learn from the teachers.
	Our training objective allows seamless
	addition of teacher translation paths
	for any given low resource pair. Since our
	approach relies on the quality of monolingual
	word embeddings, we also propose to
	enhance vector representations of both the
	source and target language with linguistic
	information. Our experiments on various
	languages show large performance gains
	from our distillation training objective, obtaining
	as high as 17% accuracy improvements.},
  url       = {https://www.aclweb.org/anthology/D17-1264}
}