@inproceedings{han-etal-2018-conditional,
    title = "Conditional Word Embedding and Hypothesis Testing via {B}ayes-by-Backprop",
    author = "Han, Rujun  and
      Gill, Michael  and
      Spirling, Arthur  and
      Cho, Kyunghyun",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D18-1527/",
    doi = "10.18653/v1/D18-1527",
    pages = "4890--4895",
    abstract = "Conventional word embedding models do not leverage information from document meta-data, and they do not model uncertainty. We address these concerns with a model that incorporates document covariates to estimate conditional word embedding distributions. Our model allows for (a) hypothesis tests about the meanings of terms, (b) assessments as to whether a word is near or far from another conditioned on different covariate values, and (c) assessments as to whether estimated differences are statistically significant."
}