This book brings a basic yet detailed description of Icelandic nominalizations to bear on the
general theoretical and architectural issues that nominalizations have raised since the …

The recent increase in data and model scale for language model pre-training has led to
huge training costs. In scenarios where new data become available over time, updating a …

Social changes in late modernity have implications for the ways in which variation in
Icelandic language use comes to be associated with different modes of communication, and …

In this paper we describe how a fairly new CLARIN member is building a broad collection of
national language resources for use in language technology (LT). As a CLARIN C-centre …

Smaller LLMs still face significant challenges even in medium-resourced languages,
particularly when it comes to language-specific knowledge--a problem not easily resolved …

We train and evaluate four Part-of-Speech tagging models for Icelandic. Three are older
models that obtained the highest accuracy for Icelandic when they were introduced. The …

A corpus study of að-infinitives in Icelandic reveals important data that have so far gone
unnoticed in the theoretical literature. The study shows that Icelandic allows split infinitives …

Recent research has shown that utilizing preference training methods, such as
reinforcement learning from human feedback (RLHF) or direct preference optimization …

Part-of-Speech (POS) tagging is a sequential labelling task in which words, punctuation, and
symbols occurring in running text, ie, tokens are assigned a tag describing their …

In this paper, we draw on corpus data to show that in Icelandic, verbs that assign distinct
cases can be coordinated and share a single object: the verb on the right determines the …