N-gram graphs offer a generic representation and a related framework for the representation and handling of symbol sequences. They encode neighbourhood information between items expressing both local and global characteristics of the sequences in a manner that supports uncertainty. They have been applied successfully to several tasks, such as news summarization (NewSum method) and news summarization evaluation (AutoSummENG, MeMoG, NPowER methods). N-gram graphs can also co-exist with and empower existing machine learning algorithms in the vector space. Thus, they have been applied in this combined manner in settings including sentiment analysis, topic-based classification, adaptive systems and even bioinformatics. In this presentation we will discuss what n-gram graphs are – and what they are not -, their application and level of success in the above settings and how one can exploit their power to tackle existing and new scientific challenges.
*The lecture will be broadcast live to the Dalhousie University, Canada; priority will be given to remote questions.