KMi Seminars
LSA-based Cognitive Models
This event took place on Wednesday 01 December 2010 at 11:30

 
Sonia Mandin Université Pierre-Mendès-France

This seminar concerns the design of technology enhanced learning environments to improve their learning through reading and writing activities. So far, We have tested (1) The effect of informative feedback on the computerized note-taking from an online course with students, (2) The effect of feedback on the production of a summary or a synthesis on the control of these activities and the understanding of the documents read and researches from students about the European project LTfLL.

Among these various studies, the most important research concerns the summary activity, an activity that allows learners to train their understanding and to assess it.

A large part of the work presented in this seminar relates to the computational modeling of cognitive processes used in understanding and writing activities. These models allow us to better understand the learner. They are based on latent semantic analysis and are used for predictive purposes in the systems designed.

More generally, with an original approach based on theories borrowed from different fields (psychological, educational, computer), we are trying to answer the question: how to assist learners to improve their reading comprehension and written production?

(Due to a combination of factors including a change of venue we were unable to record this event, we apologise to those who were otherwise unable to attend this event in person)

 
KMi Seminars Event | SSSW 2013, The 10th Summer School on Ontology Engineering and the Semantic Web Journal | 25 years of knowledge acquisition
 

Multimedia and Information Systems is...


Multimedia and Information Systems
Our research is centred around the theme of Multimedia Information Retrieval, ie, Video Search Engines, Image Databases, Spoken Document Retrieval, Music Retrieval, Query Languages and Query Mediation.

We focus on content-based information retrieval over a wide range of data spanning form unstructured text and unlabelled images over spoken documents and music to videos. This encompasses the modelling of human perception of relevance and similarity, the learning from user actions and the up-to-date presentation of information. Currently we are building a research version of an integrated multimedia information retrieval system MIR to be used as a research prototype. We aim for a system that understands the user's information need and successfully links it to the appropriate information sources, be it a report or a TV news clip. This work is guided by the vision that an automated knowledge extraction system ultimately empowers people making efficient use of information sources without the burden of filing data into specialised databases.

Visit the MMIS website