© 2016 Swiss Alliance for Data-Intensive Services

  • Twitter Basic Black

Gregory Grefenstette - Personal information systems and personal semantics


Wearable device are capturing more of our everyday life, allowing us to passively create a “lifelog” record of our activities. Current research in lifelog data has not paid enough attention to analysis of cognitive activities in comparison to physical activities. We argue that as we look into the future, wearable devices are going to be cheaper and more prevalent and textual data will play a more significant role. Data captured by lifelogging devices will increasingly include speech and text, potentially useful in analysis of intellectual activities. Analysing what a person hears, reads, and sees, we should be able to measure the extent of cognitive activity devoted to a certain topic or subject by a learner. Test-based lifelog records can benefit from semantic analysis tools developed for natural language processing.  We show how semantic analysis of such text data can be achieved through the use of taxonomic subject facets and how these facets might be useful in quantifying cognitive activity devoted to various topics in a person’s day. We are currently developing a method to automatically create taxonomic topic vocabularies that can be applied to this detection of intellectual activity. We will illustrate this in a private personal information platform we have developed.


Gregory Grefenstette is senior associate researcher at the Florida Institute for Human & Machine Cognition (IHMC). He is a leading researcher in the field of natural language processing, helping to pioneer the fields of cross-language information retrieval and of distributional semantics, the induction and extraction of meaning from large quantities of text. Previous to his association with IHMC, Dr. Grefenstette was Advanced Researcher at Inria, the French national research institute in Computer Science, working on personal semantics, automatically creating taxonomies of personal interest such as hobbies and illnesses, used to annotate big personal data generated by a person’s interaction with the digital world. Prior to that he was Chief Science Officer of Exalead, a search engine company, managing the OSEO QUAERO CMSE program on innovative multimedia indexing. Former chief scientist at the Xerox Research Centre Europe (1993-2001), at Clairvoyance Corporation (2001-2004), and with the French CEA (2004-2008), Dr. Grefenstette has been active in transferring research into products, and is named as inventor in 20 U.S patents. His research teams have been awarded the ACM Multimedia Grand Challenge 2010 Bronze award for “Introducing topic segmentation and segmented-based browsing tools into a content based video retrieval system” the ACM Multimedia Grand Challenge 2009 Award Most Practical System: “VoxaleadNews: Robust Automatic Segmentation of Video into Browsable Content” and a Lagardere Foundation 2007 three year grant for “Semantic Maps”. Dr. Grefenstette is the author and editor of the following books: Search Based Applications (with Laura Wilber, Morgan Claypool, 2011), Text- and Speech-Triggered Information Access (Ed. With Steve Renals, Springer 2003) Cross-Language Information Retrieval (Ed. Kluwer, 1998) Explorations in Automatic Thesaurus Discovery (Kluwer, 1994)

Please reload