@InProceedings{vulic-EtAl:2017:Long,
  author    = {Vuli\'{c}, Ivan  and  Mrk\v{s}i\'{c}, Nikola  and  Reichart, Roi  and  \'{O} S\'{e}aghdha, Diarmuid  and  Young, Steve  and  Korhonen, Anna},
  title     = {Morph-fitting: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {56--68},
  abstract  = {Morphologically rich languages accentuate two properties of distributional
	vector space models: 1) the difficulty of inducing accurate representations for
	low-frequency word forms; and 2) insensitivity to distinct lexical relations
	that have similar distributional signatures. These effects are detrimental for
	language understanding systems, which may infer that  'inexpensive' is a
	rephrasing for 'expensive' or may not associate 'acquire' with 'acquires'. In
	this work, we propose a novel morph-fitting procedure which moves past the use
	of curated semantic lexicons for improving distributional vector spaces.
	Instead, our method injects morphological constraints generated using simple
	language-specific rules, pulling inflectional forms of the same word close
	together and pushing derivational antonyms far apart. In intrinsic evaluation
	over four languages, we show that our approach: 1) improves low-frequency word
	estimates; and 2) boosts the semantic quality of the entire word vector
	collection. Finally, we show that morph-fitted vectors yield large gains in the
	downstream task of dialogue state tracking, highlighting the importance of
	morphology for tackling long-tail phenomena in language understanding tasks.},
  url       = {http://aclweb.org/anthology/P17-1006}
}