Projects
Scrolls before the Sect(s): the Aramaic and the Sapiential Texts in the Dead Sea Scrolls Corpus. KU Leuven
The European Parliament Parallel Intermodal Corpus Ghent (EPPIC-G) Ghent University
This project aims at (1) enlarging an existing interpreting corpus of around 220.000 words, compiled at Ghent University and storing it in EXMARaLDA; (2) tranforming it into a parallel intermodal corpus by adding the corresponding translations, and (3) making the data available and searchable through a web interface.
A corpus linguistic approach of Classical Hebrew: a pilot project KU Leuven
Special Research Fund Professorship in Bantu Corpus Linguistics Ghent University
A BOF-ZAP-mandate holder receives an appointment or appointment as a member of the Independent Academic Personnel with mainly research assignment. The wage costs are charged to the resources of the BOF.
Measuring norm conformity in Belgian-Dutch subtitling: a multivariate corpus study Ghent University
By means of a corpus-based study, we investigate whether language use in Belgian-Dutch subtitles differs lexically and grammatically from written translated and non-translated text genres and whether this linguistic behavior depends on specific contextual factors.
An evaluation corpus for automatic summarization. University of Antwerp
PLATOS: Detection of topics, stance and argumentation in a social media corpus Ghent University
This proposal aims at investigating stance and argument detection on automatically extracted topics in social media text by combining linguistic knowledge and machine learning. The proposed research is innovative in
two respects: (1) term extraction and hypernym detection techniques will be combined with distributional information to detect topics and (2) a model for argumentation mining in social media text will be researched.
Poetry from the Margins. Literary, Philological, minguistic and historical analysis of a new corpus of byzantine Book Epigrams (800-1453) Ghent University
Literary, linguistic and historical analysis of a corpus of book epigrams from medieval Greek manuscripts. Unknown texts will be published with a commentary, both in paper version and on-line. The analysis will shed new light on the literary aesthetics of the Byzantine period, the evolution of medieval Greek language, orthography and verse forms, and the socio-historical context of the emergence of books and manuscripts.