State-of-the-art statistical approaches to the Coreference Resolution task rely on sophisticated modeling, but very few (10-20) simple features. In this paper we propose to extend the standard feature set substantially, incorporating more linguistic knowledge. To investigate the usability of linguistically motivated features, we evaluate our system for a variety of machine learners on the stand...

CLaC-CORE, an exhaustive feature combination system ranked 4th among 34 teams in the Semantic Textual Similarity shared task STS 2013. Using a core set of 11 lexical features of the most basic kind, it uses a support vector regressor which uses a combination of these lexical features to train a model for predicting similarity between sentences in a two phase method, which in turn uses all combi...

Hypertension Complicating Carotid Endarterectomy • Fifteen of 27 patients became hypertensive after unilateral carotid endarterectomy; seven of these experienced neurological deterioration, which persisted more than a week in five patients. Neurological worsening did not occur in patients without postoperative hypertension, which developed primarily in patients with a preoperative disturbance o...

In some fields, Big Data has been instrumental in analyzing, predicting, and influencing human behavior. However, Big Data approaches have so far been less central in speech-language pathology. This article introduces the concept of Big Data and provides examples of Big Data initiatives pertaining to adult neurorehabilitation. It also discusses the potential theoretical and clinical contributio...

s / Journal of the Neurological Sciences xxx (2015) xxx–xxx 2