Semantic Structure and Interpretability of Word Embeddings

@article{x015Eenel2018SemanticSA,
  title={Semantic Structure and Interpretability of Word Embeddings},
  author={Lx00FCtfi Kerem x015Eenel and x0130hsan Utlu and Veysel Yx00FCcesoy and Aykut Kox00E7 and Tolga x00C7ukur},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year={2018},
  volume={26},
  pages={1769-1779}
}
Dense word embeddings, which encode meanings of words to low-dimensional vector spaces, have become very popular in natural language processing (NLP) research due to their state-of-the-art performances in many NLP tasks. Word embeddings are substantially successful in capturing semantic relations among words, so a meaningful semantic structure must be present in the respective vector spaces. However, in many cases, this semantic structure is broadly and heterogeneously distributed across the… CONTINUE READING