In this paper, we present the D-TUNA corpus, which is the first semantically annotated corpus of referring expressions in Dutch. Its primary function is to evaluate and improve th...
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
Interaction between two teams with the same team leader and with similar size and goals moved from weekly face-to-face meetings to virtual meetings because of the temporary displac...
Marilyn Tremaine, Allen E. Milewski, Richard Egan,...
We present the main findings and preliminary results of an ongoing project aimed at developing a system for collocation extraction based on contextual morpho-syntactic properties....
Amalia Todirascu, Dan Tufis, Ulrich Heid, Christop...
In this paper, we present an original framework to model frame semantic resources (namely, FrameNet) using minimal supervision. This framework can be leveraged both to expand an e...
Marco Pennacchiotti, Diego De Cao, Paolo Marocco, ...