Learn More
Most attempts to integrate FrameNet in NLP systems have so far failed because of its limited coverage. In this paper, we investigate the applicability of distributional and WordNet-based models on the task of lexical unit induction , i.e. the expansion of FrameNet with new lexical units. Experimental results show that our distributional and WordNet-based(More)
State-of-the-art semantic role labelling systems require large annotated corpora to achieve full performance. Unfortunately, such corpora are expensive to produce and often do not generalize well across domains. Even in domain, errors are often made where syntactic information does not provide sufficient cues. In this paper , we mitigate both of these(More)
We consider the filtering problem in linear state space models with heavy tailed process and measurement noise. Our work is based on Student's t distribution, for which we give a number of useful results. The derived filtering algorithm is a generalization of the ubiquitous Kalman filter, and reduces to it as special case. Both Kalman filter and the new(More)
The human soleus H-reflex is commonly tested as an indicator of the reflex excitability of the calf muscles with infrequent stimuli to a subject seated and at rest. However, the reflex varies widely with the level of voluntary contraction and with the time history of stimulation. We studied two aspects of this variation. Antagonist (tibialis anterior)(More)
Discourse coherence is an important aspect of natural language that is still understudied in computational linguistics. Our aim is to learn factors that constitute coherent discourse from data, with a focus on how to realize predicate-argument structures (PAS) in a model that exceeds the sentence level. In particular, we aim to study the case of(More)
The second order extended Kalman filter (EKF2) is based on a second order Taylor expansion of a nonlinear system, in contrast to the more common (first order) extended Kalman filter (EKF1). Despite a solid theoretical ground for its approximation, it is seldom used in applications, where the EKF and the unscented Kalman filter (UKF) are the standard(More)
Generating coherent discourse is an important aspect in natural language generation. Our aim is to learn factors that constitute coherent discourse from data, with a focus on how to realize predicate-argument structures in a model that exceeds the sentence level. We present an important subtask for this overall goal, in which we align predicates across(More)
For many years, the convergence of Internet data services and transport network services based on optical transmission has been at the heart of carriers' investments and business strategies. Over time, the inherent segmentation of IP and transport networks has created major technology differences, thus impacting their management and operation. In addition,(More)