Abstract. We present a linguistically-motivated sub-sentential alignment system that extends the intersected IBM Model 4 word alignments. The alignment system is chunk-driven and r...
We describe a new method for extracting Negative Polarity Item candidates (NPI candidates) from dependency-parsed German text corpora. Semi-automatic extraction of NPIs is a chall...
Existing methods of information extraction from HTML documents include manual approach, supervised learning and automatic techniques. The manual method has high precision and reca...
Mirel Cosulschi, Adrian Giurca, Bogdan Udrescu, Ni...
Abstract. The signaling traffic of a cellular network is rich of information related to the movements of its devices across cell boundaries. Thus, passive monitoring of anonymized ...
A number of metadata standards have been published in recent years due to the increasing availability of multimedia content and the resulting issue of sorting and retrieving this ...
Matthias Gruhne, Christian Uhle, Christian Dittmar...