no code implementations • 8 Jun 2016 • Gregory Grefenstette, Lawrence Muchemi
Data captured by lifelogging devices will increasingly include speech and text, potentially useful in analysis of intellectual activities.
no code implementations • 31 May 2016 • Gregory Grefenstette, Lawrence Muchemi
Terms which are found significantly more often in the specialized corpus than in the background corpus are candidates for the characteristic vocabulary of the domain.
no code implementations • LREC 2016 • Gregory Grefenstette
One basic element of language models is the list of words in a language.
no code implementations • 4 Nov 2015 • Gregory Grefenstette, Karima Rafes
Here we describe how we can connect local information to Wikipedia, without altering its content.
no code implementations • SEMEVAL 2015 • Gregory Grefenstette
Given a set of terms from a given domain, how can we structure them into a taxonomy without manual intervention?
no code implementations • 23 Jun 2000 • Gregory Grefenstette, Julien Nioche
The World Wide Web has grown so big, in such an anarchic fashion, that it is difficult to describe.