Nowadays a search engine such as Google goes beyond presenting to the user a list of results relevant to some query. Consider for instance asking Google about an important artist such as Leonardo da Vinci. Apart from the list of relevant results, Google quite conveniently presents to the user an information box that includes specific facts about this artist.
This summarised information includes images of da Vinci himself, as well as images of his most well-known paintings, such as the Mona Lisa. There is also information related to when the artist was born and where, when and where he died, who his siblings were, his most popular quotes and much more. The information is furthermore navigable as there are embedded hyperlinks that allow the user to follow specific information trails.
One can think about this as a kind of knowledge map, with information excerpts linked to other excerpts. In fact, Google refers to the underlying structure as a ‘knowledge graph’, a term coined by the company in 2012 and synonymous to an advanced knowledge base of facts.
The term ‘graph’ in this case is related to the mathematical structure used to model pairwise relations between objects. These objects are referred to as vertices and are connected with each other by edges. When applied to the concept of a knowledge graph, the vertices can represent entities such as people, cities, books or games, while the edges can represent relations that link entities together. For instance, in the knowledge graph about Leonardo da Vinci, vertices represent the artist and his painting, while the fact that this artist painted the Mona Lisa is represented by an edge.
Research associated with knowledge graphs has its roots in a field of artificial intelligence called ‘knowledge representation and reasoning’ that focuses on representing information about the world in a form that can be exploited by computers.
The Department of Artificial Intelligence at the University of Malta is involved in research related to the application of knowledge graphs and machine learning to a variety of domains including healthcare and cultural heritage.
In healthcare, the focus is on patient-centric research that leverages on a knowledge graph where all the individual’s medical history, examinations and imagery are connected together to provide healthcare professionals with a comprehensive view for each individual patient.
Our research in the area of cultural heritage intends to bring to life an archive of notarial manuscripts from the Notarial Archives in Valletta and dating back to the 15th century by creating a knowledge graph of linked notaries and deeds to facilitate the work of professionals and historians.
The challenges are varied and depend on the domain and information that the knowledge graph is representing. Machine learning techniques are important to automate the extraction of information from digitised content, as well as to provide ways on how to make the knowledge more complete.
Dr Charlie Abela is a lecturer with the Department of Artificial Intelligence at the University of Malta.
Did you know?
• The average heart is the size of a fist in an adult.
• The earliest known case of heart disease was identified in the remains of a 3,500-year-old Egyptian mummy.
• The iconic heart shape as a symbol of love is traditionally thought to come from the silphium plant, which was used as an ancient form of birth control.
• Laughing is good for your heart. It reduces stress and gives a boost to your immune system.
For more trivia see: www.um.edu.mt/think
Sound bites
• A team at the University of Washington created a method that allows three people to play a Tetris-like game using a brain-to-brain interface. This is the first demonstration of two things: a brain-to-brain network of more than two people and a person being able to both receive and send information to others using only their brain. The team hopes that these results will pave the way for future brain-to-brain interfaces that allow people to collaborate to solve tough problems that one brain alone couldn’t solve.
https://www.sciencedaily.com/releases/2019/07/190701163827.htm
• The International Space Station, like all human habitats in space, has a nagging mould problem. Astronauts on the ISS spend hours every week cleaning the inside of the station’s walls to prevent mould from becoming a health problem. New research being presented has found that mould spores may also survive on the outside walls of a spacecraft. Spores of the two most common types of mould on the ISS, Aspergillus and Penicillium, survive X-ray exposure at 200 times the dose that would kill a human.
https://www.sciencedaily.com/releases/2019/06/190627121252.htm
For more soundbites listen to Radio Mocha on Mondays at 7pm on Radju Malta and Thursdays at 4pm on Radju Malta 2 https://www.fb.com/RadioMochaMalta/