@inproceedings{remus-biemann-2016-domain,
    title = "Domain-Specific Corpus Expansion with Focused Webcrawling",
    author = "Remus, Steffen  and
      Biemann, Chris",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Grobelnik, Marko  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, Helene  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
    month = may,
    year = "2016",
    address = "Portoro{\v{z}}, Slovenia",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/landing_page/L16-1572/",
    pages = "3607--3611",
    abstract = "This work presents a straightforward method for extending or creating in-domain web corpora by focused webcrawling. The focused webcrawler uses statistical N-gram language models to estimate the relatedness of documents and weblinks and needs as input only N-grams or plain texts of a predefined domain and seed URLs as starting points. Two experiments demonstrate that our focused crawler is able to stay focused in domain and language. The first experiment shows that the crawler stays in a focused domain, the second experiment demonstrates that language models trained on focused crawls obtain better perplexity scores on in-domain corpora. We distribute the focused crawler as open source software."
}