Language Technology Group's repositories
simple_elmo
Simple library to work with pre-trained ELMo models in TensorFlow
talk-of-norway
This repository makes available the Talk of Norway (ToN) dataset, a collection of Norwegian parliament speeches from 1998 to 2016. Every speech is richly annotated with metadata pulled from different sources, and augmented with sentence, token, lemma, part-of-speech and morphological feature annotations.
simple_elmo_training
Minimal code to train ELMo models in recent versions of TensorFlow
definition_modeling
Interpretable Word Sense Representations via Definition Generation
axolotl24_shared_task
AXOLOTL-24 (Ascertain and eXplain Overhauls of the Lexicon Over Time at LChange'24): a shared task
nor_dia_change
Manually annotated dataset of diachronic semantic change in Norwegian
wugs_with_definitions
Methods that annotate word occurrences with glosses describing their meaning.
ai_nlp_benchmark
NLP benchmark for multiple GPUs
LetHerLearn
Repository for the LetHerLearn dataset of emotion-annotated tweets covering the ban of education in Afghanistan
NoMusic
The Norwegian Multi-Dialectal Slot and Intent Detection Corpus
norec_sentence
Aggregated datasets for sentence-level sentiment classification in Norwegian
Sentiment-Annotation-of-Patient-Comments
A repository for the work done on sentiment analysis on patient free-text comments