1 code implementation • EACL (HumEval) 2021 • Goya van Boven, Jelke Bloem
We evaluate the use of direct intrinsic word embedding evaluation tasks for specialized language.
1 code implementation • NAACL 2021 • Yvette Oortwijn, Jelke Bloem, Pia Sommerauer, Francois Meyer, Wei Zhou, Antske Fokkens
We investigate the possibilities and limitations of using distributional semantic models for analyzing philosophical data by means of a realistic use-case.
2 code implementations • COLING 2020 • Arianna Betti, Martin Reynaert, Thijs Ossenkoppele, Yvette Oortwijn, Andrew Salway, Jelke Bloem
We present a novel, domain expert-controlled, replicable procedure for the construction of concept-modeling ground truths with the aim of evaluating the application of word embeddings.
no code implementations • LREC 2020 • Jelke Bloem, Maria Chiara Parisi, Martin Reynaert, Yvette Oortwijn, Arianna Betti
Our results show that consistent Neo-Latin word embeddings can be learned from this type of data.
no code implementations • RANLP 2019 • Jelke Bloem, Antske Fokkens, Aur{\'e}lie Herbelot
Specifically, we inspect the behaviour of models using a pre-trained background space in learning.
no code implementations • WS 2019 • Jelke Bloem, Arjen Versloot, Fred Weerman
Certain phenomena of interest to linguists mainly occur in low-resource languages, such as contact-induced language change.
no code implementations • WS 2016 • Jelke Bloem
We investigate a particular variation phenomenon, word order variation in Dutch two-verb clusters, where it has been established that word order choice is affected by processing cost.