Building Web Corpora for Minority Languages

Web corpora creation for minority languages that do not have their own top-level Internet domain is no trivial matter. Web pages in such minority languages often contain text and links to pages in the dominant language of the country. When building corpora in specific languages, one has to decide how and at which stage to make sure the texts gathered are in the desired language. In the {``}Finno-Ugric Languages and the Internet{''} (Suki) project, we created web corpora for Uralic minority languages using web crawling combined with a language identification system in order to identify the language while crawling. In addition, we used language set identification and crowdsourcing before making sentence corpora out of the downloaded texts. In this article, we describe a strategy for collecting textual material from the Internet for minority languages. The strategy is based on the experiences we gained during the Suki project.