BibTeX

@inProceedings{nietopina-johansson-2017-training-261938,
	title        = {Training Word Sense Embeddings With Lexicon-based Regularization},
	abstract     = {We propose to improve word sense embeddings by enriching an automatic corpus-based method with lexicographic data. Information from a lexicon is introduced into the learning algorithm’s objective function through a regularizer. The incorporation of lexicographic data yields embeddings that are able to reflect expertdefined word senses, while retaining the robustness, high quality, and coverage of automatic corpus-based methods. These properties are observed in a manual inspection of the semantic clusters that different degrees of regularizer strength create in the vector space. Moreover, we evaluate the sense embeddings in two
downstream applications: word sense disambiguation and semantic frame prediction, where they outperform simpler approaches. Our results show that a corpusbased model balanced with lexicographic data learns better representations and improve their performance in downstream tasks},
	booktitle    = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Taipei, Taiwan, November 27 – December 1, 2017},
	author       = {Nieto Piña, Luis and Johansson, Richard},
	year         = {2017},
	publisher    = {Asian Federation of Natural Language Processing },
	ISBN         = {978-1-948087-00-1},
}