@inproceedings{vor-der-bruck-pouly-2019-text,
    title = "Text Similarity Estimation Based on Word Embeddings and Matrix Norms for Targeted Marketing",
    author = {vor der Br{\"u}ck, Tim  and
      Pouly, Marc},
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/N19-1181/",
    doi = "10.18653/v1/N19-1181",
    pages = "1827--1836",
    abstract = "The prevalent way to estimate the similarity of two documents based on word embeddings is to apply the cosine similarity measure to the two centroids obtained from the embedding vectors associated with the words in each document. Motivated by an industrial application from the domain of youth marketing, where this approach produced only mediocre results, we propose an alternative way of combining the word vectors using matrix norms. The evaluation shows superior results for most of the investigated matrix norms in comparison to both the classical cosine measure and several other document similarity estimates."
}