Essential speech and language technology for Dutch

P Spyns, J Odijk - Results by the STEVIN programme: Springer, 2013 - Springer
Summarising a research programme that lasted for more than 6 years is a demanding task
due to the wealth of deliverables, publications and final results of each of the projects …

[PDF][PDF] Dutchsemcor: in quest of the ideal sense-tagged corpus

P Vossen, R Izquierdo, A Görög - Proceedings of the international …, 2013 - aclanthology.org
The most-frequent-sense and the predominant domain sense play an important role in the
debate on word-sensedisambiguation. This discussion is, however, biased by the way …

[PDF][PDF] Essential Speech and Language Technology for Dutch: Results by the STEVIN-programme

JO Peter Spyns - 2013 - library.oapen.org
Summarising a research programme that lasted for more than 6 years is a demanding task
due to the wealth of deliverables, publications and final results of each of the projects …

Theory and Applications of Natural Language Processing

G Hirst, E Hovy, M Johnson - 2013 - Springer
“Theory and Applications of Natural Language Processing” is a series of volumes dedicated
to selected topics in NLP and Language Technology. It focuses on the most recent advances …

[PDF][PDF] Named-entity recognition: a gateway drug for cultural heritage collections to the linked data cloud

S van Hooland, M De Wilde, R Verborgh… - Literary and Linguistic …, 2013 - tomayac.com
Unstructured metadata fields such as 'description'offer tremendous value for users to
understand cultural heritage objects. However, this type of narrative information is of little …

What replication and localisation teach us: the case of semantic similarity measures

MC Postma - 2013 - studenttheses.uu.nl
Many tasks in the field of Natural Language Processing make use of so-called semantic
similarity measures, which quantify the degree to which two concepts are semantically …

[PDF][PDF] Unsupervised identification of compounds

N van Noord, M van Zaanen - academia.edu
In a variety of languages, compounds (ie, lexemes consisting of more than one stem) are
written as one token. Identifying such compounds together with their compound boundaries …