CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions

@inproceedings{Tian2018CoVeRLC,
  title={CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions},
  author={Kevin Tian and Teng Zhang and James Zou},
  booktitle={ICML},
  year={2018}
}
Word embedding is a useful approach to capture co-occurrence structures in large text corpora. However, in addition to the text data itself, we often have additional covariates associated with individual corpus documents—e.g. the demographic of the author, time and venue of publication—and we would like the embedding to naturally capture this information… CONTINUE READING