@InProceedings{simov-boytcheva-osenova:2017:RANLP,
  author    = {Simov, Kiril  and  Boytcheva, Svetla  and  Osenova, Petya},
  title     = {Towards Lexical Chains for Knowledge-Graph-based Word Embeddings},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017},
  month     = {September},
  year      = {2017},
  address   = {Varna, Bulgaria},
  publisher = {INCOMA Ltd.},
  pages     = {679--685},
  abstract  = {Word vectors with varying dimensionalities and produced by different algorithms
	have been extensively used in NLP. The corpora that the algorithms are trained
	on can contain either natural language text (e.g. Wikipedia or newswire
	articles) or artificially-generated pseudo corpora due to natural data
	sparseness.
	We exploit Lexical Chain based templates over Knowledge Graph for generating
	pseudo-corpora with controlled linguistic value. These corpora are then used
	for learning word embeddings. A number of experiments have been conducted over
	the following test sets: WordSim353 Similarity, WordSim353 Relatedness and
	SimLex-999.
	The results show that, on the one hand, the incorporation of many-relation
	lexical chains improves results, but on the other hand, unrestricted-length
	chains remain difficult to handle with respect to their huge quantity.},
  url       = {https://doi.org/10.26615/978-954-452-049-6_087}
}