@inproceedings{20baf405d3bc46c286758b81298a5a7e,
title = "An exploration of language identification techniques for the Dutch folktale database",
abstract = "The Dutch Folktale Database contains fairy tales, traditional legends, urban legends, and jokes written in a large variety and combination of languages including (Middle and 17th century) Dutch, Frisian and a number of Dutch dialects. In this work we compare a number of approaches to automatic language identification for this collection. We show that in comparison to typical language identification tasks, classification performance for highly similar languages with little training data is low. The studied dataset consisting of over 39,000 documents in 16 languages and dialects is available on request for followup research.",
keywords = "METIS-289720, IR-82013, EWI-22321, Text classification, HMI-SLT: Speech and Language Technology, Language detection",
author = "Trieschnigg, {Rudolf Berend} and Djoerd Hiemstra and Mariet Theune and {de Jong}, {Franciska M.G.} and Theo Meder",
year = "2012",
month = may,
day = "26",
language = "Undefined",
isbn = "not assigned",
publisher = "LREC organization",
pages = "47--51",
editor = "P. Osenova and S. Piperidis and M. Slavcheva and C. Vertan",
booktitle = "Proceedings of the Workshop on Adaptation of Language Resources and Tools for Processing Cultural Heritage (LREC 2012)",
note = "Workshop on Adaptation of Language Resources and Tools for Processing Cultural Heritage, LREC 2012 ; Conference date: 26-05-2012 Through 26-05-2012",
}