@inproceedings{hellrich-etal-2019-influence,
    title = "The Influence of Down-Sampling Strategies on {SVD} Word Embedding Stability",
    author = "Hellrich, Johannes  and
      Kampe, Bernd  and
      Hahn, Udo",
    editor = "Rogers, Anna  and
      Drozd, Aleksandr  and
      Rumshisky, Anna  and
      Goldberg, Yoav",
    booktitle = "Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for {NLP}",
    month = jun,
    year = "2019",
    address = "Minneapolis, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W19-2003/",
    doi = "10.18653/v1/W19-2003",
    pages = "18--26",
    abstract = "The stability of word embedding algorithms, i.e., the consistency of the word representations they reveal when trained repeatedly on the same data set, has recently raised concerns. We here compare word embedding algorithms on three corpora of different sizes, and evaluate both their stability and accuracy. We find strong evidence that down-sampling strategies (used as part of their training procedures) are particularly influential for the stability of SVD-PPMI-type embeddings. This finding seems to explain diverging reports on their stability and lead us to a simple modification which provides superior stability as well as accuracy on par with skip-gram embedding"
}