This paper presents the results of the news translation task, the multilingual low-resource
translation for Indo-European languages, the triangular translation task, and the automatic …

This paper presents the ParlaMint corpora containing transcriptions of the sessions of the 17
European national parliaments with half a billion words. The corpora are uniformly encoded …

We train several language models for Icelandic, including IceBERT, that achieve state-of-the-
art performance in a variety of downstream tasks, including part-of-speech tagging, named …

In this paper, we describe a new national language technology programme for Icelandic.
The programme, which spans a period of five years, aims at making Icelandic usable in …

Lemmatization, finding the basic morphological form of a word in a corpus, is an important
step in many natural language processing tasks when working with morphologically rich …

Previous work on using BiLSTM models for PoS tagging has primarily focused on small
tagsets. We evaluate BiLSTM models for tagging Icelandic, a morphologically rich language …

In this paper, we evaluate several Transformer-based language models for Icelandic on four
downstream tasks: Part-of-Speech tagging, Named Entity Recognition. Dependency …

The topic of this paper is The Database of Icelandic Morphology (DIM), a multipurpose
linguistic resource, created for use in language technology, as a reference for the general …

Danish language technology has been hindered by a lack of broad-coverage corpora at the
scale modern NLP prefers. This paper describes the Danish Gigaword Corpus, the result of …

Grammatical error correction (GEC) is the task of correcting typos, spelling, punctuation and
grammatical issues in text. Approaching the problem as a sequence-to-sequence task, we …