@inproceedings{nikolov-hahnloser-2019-large,
    title = "Large-Scale Hierarchical Alignment for Data-driven Text Rewriting",
    author = "Nikolov, Nikola I.  and
      Hahnloser, Richard",
    editor = "Mitkov, Ruslan  and
      Angelova, Galia",
    booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
    month = sep,
    year = "2019",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd.",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/R19-1098/",
    doi = "10.26615/978-954-452-056-4_098",
    pages = "844--853",
    abstract = "We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news articles and scientific papers. Our approach does not require a seed parallel corpus, but instead relies solely on hierarchical search over pre-trained embeddings of documents and sentences. We demonstrate the effectiveness of our method through automatic and extrinsic evaluation on text simplification from the normal to the Simple Wikipedia. We show that pseudo-parallel sentences extracted with our method not only supplement existing parallel data, but can even lead to competitive performance on their own."
}