@InProceedings{lee-chen:2017:EMNLP2017,
  author    = {Lee, Guang-He  and  Chen, Yun-Nung},
  title     = {MUSE: Modularizing Unsupervised Sense Embeddings},
  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     = {327--337},
  abstract  = {This paper proposes to address the word sense ambiguity issue in an
	unsupervised manner, where word sense representations are learned along a word
	sense selection mechanism given contexts. Prior work focused on designing a
	single model to deliver both mechanisms, and thus suffered from either
	coarse-grained representation learning or inefficient sense selection. The
	proposed modular approach, MUSE, implements flexible modules to optimize
	distinct mechanisms, achieving the first purely sense-level representation
	learning system with linear-time sense selection. We leverage reinforcement
	learning to enable joint training on the proposed modules, and introduce
	various exploration techniques on sense selection for better robustness. The
	experiments on benchmark data show that the proposed approach achieves the
	state-of-the-art performance on synonym selection as well as on contextual word
	similarities in terms of MaxSimC.},
  url       = {https://www.aclweb.org/anthology/D17-1034}
}