POS tagging, lemmatization and dependency parsing of West Frisian
This work addresses the lack of NLP tools for West Frisian, a low-resource language, though it is incremental as it adapts existing methods from Dutch.
The authors tackled the problem of creating a lemmatizer, POS tagger, and dependency parser for West Frisian by using a corpus of 44,714 words and leveraging Dutch translations, achieving a significant improvement in lemmatization performance.
We present a lemmatizer/POS-tagger/dependency parser for West Frisian using a corpus of 44,714 words in 3,126 sentences that were annotated according to the guidelines of Universal Dependency version 2. POS tags were assigned to words by using a Dutch POS tagger that was applied to a literal word-by-word translation, or to sentences of a Dutch parallel text. Best results were obtained when using literal translations that were created by using the Frisian translation program Oersetter. Morphologic and syntactic annotations were generated on the basis of a literal Dutch translation as well. The performance of the lemmatizer/tagger/annotator when it was trained using default parameters was compared to the performance that was obtained when using the parameter values that were used for training the LassySmall UD 2.5 corpus. A significant improvement was found for `lemma'. The Frisian lemmatizer/PoS tagger/dependency parser is released as a web app and as a web service.