UDPipe Frysk
UDPipe Frysk is a web application for lemmatization, part-of-speech (PoS) tagging, and dependency parsing of Frisian texts.
The lemmatizer, tagger, and parser are trained on Frisian texts annotated according to the Universal Dependencies version 2 guidelines. The application uses UDPipe through the R package ‘udpipe’.
Next steps
A UDPipe model was trained on a Frisian corpus of 108.562 tokens, 94.640 words and 6.571 sentences. As a next step, we will add features that capture properties specific to Frisian.
The following people were involved in the development of UDPipe Frysk: Wilbert Heeringa, Gosse Bouma† (University of Groningen), Martha Hofman, Eduard Drenth (web service), Fenna Bergsma, Hans Van de Velde.
Who is involved
Wilbert Heeringa
Researcher
Wilbert Heeringa is a researcher at the Fryske Akademy, working on dialectometry, phonetics and statistics. He uses computational methods to measure dialect variation and change in vocabulary, morphology and pronunciation, and develops tools for phonetic research such as Visible Sounds.
Eduard Drenth
Software architect
Eduard Drenth is a software architect at the Fryske Akademy, where he is co-responsible for ICT policy . He is also involved in the Fryske Akademy’s language databases (Frysker) and the online Dutch-Frisian dictionary as a developer.
Hans Van de Velde
Researcher
Hans Van de Velde is a researcher in sociolinguistics at the Fryske Akademy. He studies language variation and change, multilingualism and phonetics, including the pronunciation of Frisian and Dutch in Fryslân, the evaluation of variations, and the development of experimental sociolinguistics.
