Zobrazeno 1 - 10
of 164
pro vyhledávání: '"NIELBO, KRISTOFFER"'
Autor:
Kardos, Márton, Kostkan, Jan, Vermillet, Arnault-Quentin, Nielbo, Kristoffer, Enevoldsen, Kenneth, Rocca, Roberta
Topic models are useful tools for discovering latent semantic structures in large textual corpora. Topic modeling historically relied on bag-of-words representations of language. This approach makes models sensitive to the presence of stop words and
Externí odkaz:
http://arxiv.org/abs/2406.09556
The evaluation of English text embeddings has transitioned from evaluating a handful of datasets to broad coverage across many tasks through benchmarks such as MTEB. However, this is not the case for multilingual text embeddings due to a lack of avai
Externí odkaz:
http://arxiv.org/abs/2406.02396
Autor:
Bizzoni, Yuri, Feldkamp, Pascale, Lassen, Ida Marie, Jacobsen, Mia, Thomsen, Mads Rosendahl, Nielbo, Kristoffer
In this study, we employ a classification approach to show that different categories of literary "quality" display unique linguistic profiles, leveraging a corpus that encompasses titles from the Norton Anthology, Penguin Classics series, and the Ope
Externí odkaz:
http://arxiv.org/abs/2404.04022
Autor:
Enevoldsen, Kenneth, Hansen, Lasse, Nielsen, Dan S., Egebæk, Rasmus A. F., Holm, Søren V., Nielsen, Martin C., Bernstorff, Martin, Larsen, Rasmus, Jørgensen, Peter B., Højmark-Bertelsen, Malte, Vahlstrup, Peter B., Møldrup-Dalum, Per, Nielbo, Kristoffer
Large language models, sometimes referred to as foundation models, have transformed multiple fields of research. However, smaller languages risk falling behind due to high training costs and small incentives for large companies to train these models.
Externí odkaz:
http://arxiv.org/abs/2311.07264
Autor:
Lassen, Ida Marie Schytt, Bizzoni, Yuri, Peura, Telma, Thomsen, Mads Rosendahl, Nielbo, Kristoffer Laigaard
Aesthetic preferences are considered highly subjective resulting in inherently noisy judgements of aesthetic objects, yet certain aspects of aesthetic judgement display convergent trends over time. This paper present a study that uses literary review
Externí odkaz:
http://arxiv.org/abs/2206.08697
We explore the correlation between the sentiment arcs of H. C. Andersen's fairy tales and their popularity, measured as their average score on the platform GoodReads. Specifically, we do not conceive a story's overall sentimental trend as predictive
Externí odkaz:
http://arxiv.org/abs/2112.07497
This article relies on information-theoretic measures to examine how events impacted the news for the period 1950-1995. Moreover, we present a method for event characterization in (unstructured) textual sources, offering a taxonomy of events based on
Externí odkaz:
http://arxiv.org/abs/2109.08589
Danish natural language processing (NLP) has in recent years obtained considerable improvements with the addition of multiple new datasets and models. However, at present, there is no coherent framework for applying state-of-the-art models for Danish
Externí odkaz:
http://arxiv.org/abs/2107.05295
Publikováno v:
In Structural Change and Economic Dynamics March 2024 68:298-312
Autor:
Nielbo, Kristoffer L., Haestrup, Frida, Enevoldsen, Kenneth C., Vahlstrup, Peter B., Baglini, Rebekah B., Roepstorff, Andreas
During the first wave of Covid-19 information decoupling could be observed in the flow of news media content. The corollary of the content alignment within and between news sources experienced by readers (i.e., all news transformed into Corona-news),
Externí odkaz:
http://arxiv.org/abs/2102.06505