@InProceedings{vulic-EtAl:2017:CoNLL,
  author    = {Vuli\'{c}, Ivan  and  Schwartz, Roy  and  Rappoport, Ari  and  Reichart, Roi  and  Korhonen, Anna},
  title     = {Automatic Selection of Context Configurations for Improved Class-Specific Word Representations},
  booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {112--122},
  abstract  = {This paper is concerned with identifying contexts useful for training word
	representation models for different word classes such as adjectives (A), verbs
	(V), and nouns (N). We introduce a simple yet effective framework for an
	automatic selection of class-specific context configurations. We construct a
	context configuration space based on universal dependency relations between
	words, and efficiently search this space with an adapted beam search algorithm.
	In word similarity tasks for each word class, we show that our framework is
	both effective and efficient. Particularly, it improves the Spearman's rho
	correlation with human scores on SimLex-999 over the best previously proposed
	class-specific contexts by 6 (A), 6 (V) and 5 (N) rho points. With our selected
	context configurations, we train on only 14% (A), 26.2% (V), and 33.6% (N) of
	all dependency-based contexts, resulting in a reduced training time. Our
	results generalise: we show that the configurations our algorithm learns for
	one English training setup outperform previously proposed context types in
	another training setup for English. Moreover, basing the configuration space on
	universal dependencies, it is possible to transfer the learned configurations
	to German and Italian. We also demonstrate improved per-class results over
	other context types in these two languages..},
  url       = {http://aclweb.org/anthology/K17-1013}
}