Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Mollberg, David Erik"'
In this paper, we present a character-based BiLSTM model for splitting Icelandic compound words, and show how varying amounts of training data affects the performance of the model. Compounding is highly productive in Icelandic, and new compounds are
Externí odkaz:
http://arxiv.org/abs/2004.07776
In this paper, we present a character-based BiLSTM model for splitting Icelandic compound words, and show how varying amounts of training data affects the performance of the model. Compounding is highly productive in Icelandic, and new compounds are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::70507cad259b9f16dd4d034dc7e4d081
http://arxiv.org/abs/2004.07776
http://arxiv.org/abs/2004.07776