@misc{MaierKuhnDuckhornetal., author = {Maier, Isidor Konrad and Kuhn, Johannes and Duckhorn, Frank and Kraljevski, Ivan and Sobe, Daniel and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Word Class Based Language Modeling: A Case of Upper Sorbian, LREC 2022, Marseille}, series = {Language Resources and Evaluation Conference 2022 (LREC 2022), Marseille, 2022-06-13}, journal = {Language Resources and Evaluation Conference 2022 (LREC 2022), Marseille, 2022-06-13}, doi = {10.5281/zenodo.7501145}, pages = {1}, language = {en} } @misc{MaierKuhnDuckhornetal., author = {Maier, Isidor Konrad and Kuhn, Johannes Ferdinand Joachim and Duckhorn, Frank and Kraljevski, Ivan and Sobe, Daniel and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Word Class Based Language Modeling: A Case of Upper Sorbian}, series = {Proceedings of The Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference, Marseille, France}, journal = {Proceedings of The Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference, Marseille, France}, publisher = {European Language Resources Association}, isbn = {978-2-493814-07-4}, pages = {28 -- 35}, abstract = {In this paper we show how word class based language modeling can support the integration of a small language in modern applications of speech technology. The methods described in this paper can be applied for any language. We demonstrate the methods on Upper Sorbian. The word classes model the semantic expressions of numerals, date and time of day. The implementation of the created grammars was realized in the form of finite-state-transducers (FSTs) and minimalists grammars (MGs). We practically demonstrate the usage of the FSTs in a simple smart-home speech application, that is able to set wake-up alarms and appointments expressed in a variety of spontaneous and natural sentences. While the created MGs are not integrated in an application for practical use yet, they provide evidence that MGs could potentially work more efficient than FSTs in built-on applications. In particular, MGs can work with a significantly smaller lexicon size, since their more complex structure lets them generate more expressions with less items, while still avoiding wrong expressions.}, language = {en} }