KMi Seminars
An investigation of the use of semantic web technologies to support learning
This event took place on Wednesday 16 March 2005 at 12:30

 
Michele Pasin KMi, The Open University

A search engine like google can help us find a list of resources, connected merely by a string similarity, and, as we know, many times it fails in answering our initial research question. Of course this happens because a computer can hardly understand the sense of our words, but treats them only syntactically, namely, taking into account their external shape and not their meaning.

If the normal web we browse daily can be seen as a huge repository of this kind of "meaningless" information, the project of the semantic web consists of a meta layer built on top, in order to describe it and make it more meaningful. While researchers from all over the world are trying to find the most effective ways for annotating the "old" web, new perspectives are emerging in the area of computer based learning.

In fact, in a scenario where resources are annotated and could be found on the web, instead of a normal search engine we could have an intelligent knowledge browser that, given a goal, follows some pre-existing knowledge patterns, gathering a set of resources that fulfill the goal. For example, I could ask this software agent to help me understanding a specific concept in physics, and receive back a series of knowledge elements that, properly digested, will bring me to the understanding of that concept.

This talk will introduce the theoretical and practical implications of such a knowledge browser, and the first ontological engineering of a domain, philosophy, where the browser will be instanced.

Download PowerPoint Presentation (576Kb ZIP file)

 
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