This paper studies the effects of training data on binary text classification and postulates that negative training data is not needed and may even be harmful for the task. Tradit...
The problem of programmability on modern heterogeneous multicore and future manycore embedded platforms is still not solved satisfactorily: although many existing but incompatible ...
Lattice gas cellular automata (LGCA) models provide a relatively fast means of simulating fluid flow and can give both quantitative and qualitative insights into flow patterns aro...
Mitchel Johnson, Daniel P. Playne, Kenneth A. Hawi...
Abstract. Recent approaches to component-based software engineering employ coordinating connectors to compose components into software systems. For maximum flexibility and reuse, s...
Marcello M. Bonsangue, Dave Clarke, Alexandra Silv...
The work presented in this paper explores a supervised method for learning a probabilistic model of a lexicon of VerbNet classes. We intend for the probabilistic model to provide ...