When we start to engage machines in conversation, what language will it be? While natural language is our preferred means of communication, natural language processing is by no mea...
This paper presents a novel cycle-approximate performance estimation technique for automatically generated transaction level models (TLMs) for heterogeneous multicore designs. The...
We investigate classification of non-linguistic vocalisations with a novel audiovisual approach and Long Short-Term Memory (LSTM) Recurrent Neural Networks as highly successful d...
In this paper we present a regression-based machine learning approach to email thread summarization. The regression model is able to take advantage of multiple gold-standard annot...
Jan Ulrich, Giuseppe Carenini, Gabriel Murray, Ray...
Programming efficiency of heterogeneous concurrent systems is limited by the use of lock-based synchronization mechanisms. Transactional memories can greatly improve the programmi...