Dr. Gianluca Demartini,
School of Electrical Engineering and Computer Science,
University of Queensland
St Lucia
QLD 4072 Australia
Office: +61 7 336 58325
demartini@acm.org
Gianluca Demartini is a Professor in Data Science and an ARC Future Fellow at the School of Electrical Engineering and Computer Science at the University of Queensland, Australia. He is also a Dieter Schwarz Fellow at the Technical University of Munich, Germany. His main research interests in Data Science include Information Retrieval and Responsible Artificial Intelligence. His research is currently funded by the Australian Research Council, the Swiss National Science Foundation, Meta, Google, and the Wikimedia Foundation. He received multiple Best Paper awards at Artificial Intelligence and Information Retrieval conferences. He has published more than 200 scientific papers at major computer science venues such as the ACM Web Conference, ACM SIGIR, VLDB Journal, ISWC, and ACM CHI. He is an ACM Senior Member, ACM Distinguished Speaker, and TEDx speaker. His recent research has looked at the application of AI for public good. This includes, for example, applications of AI to online misinformation detection, harmful content detection, and gender and political bias in AI. This has led him to work on fundamental research challenges including data bias management, fairness in AI, and human-artificial intelligence collaboration. He serves as associate editor for the Transactions on Graph Data and Knowledge (TGDK) Journal and for the ACM Journal of Data and Information Quality (JDIQ). He is a steering committee member for the AAAI HCOMP conference. He was PC Chair for the AAAI HCOMP conference in 2024, the International Semantic Web Conference in 2024, and for the ACM Conference on Research and Development in Information Retrieval (SIGIR) in 2022. He was General co-Chair for the ACM International Conference on Information and Knowledge Management (CIKM) 2021. He was Crowdsourcing and Human Computation Track co-Chair at WWW 2018 and co-chair for the Human Computation and Crowdsourcing Track at ESWC 2015. Before joining the University of Queensland, he was Lecturer at the University of Sheffield in UK, post-doctoral researcher at the eXascale Infolab at the University of Fribourg in Switzerland, visiting researcher at UC Berkeley, junior researcher at the L3S Research Center in Germany, and intern at Yahoo! Research in Spain. In 2011, he obtained a Ph.D. in Computer Science at the Leibniz University of Hannover focusing on Semantic Search.
Demo
This page contains a collection of links to running prototypes related to my research work.
Unfortunately, not all demos are running all the time.
How Does the Crowd Impact the Model? A tool for raising awareness of social bias in crowdsourced training data
- https://recant.cyens.org.cy/
A demo to showcase the impact of human annotator on machine learning models, developed in the context of the DESCANT project.
Common Agreement Phi
- http://agreement-measure.sheffield.ac.uk/
A tool to compute inter-rater agreement levels also including a newly proposed agreement measure designed for crowdsourcing enviroments.
TRank: Ranking Entity Types Using the Web of Data
- http://trank.exascale.info
A REST API for entity annotation and entity type selection in text. You can provide a webpage URL or a piece of text to get the list of entities and their types contained in the text. The API can be used programmatically as well.
B-hist: Entity-Centric Search over Personal Web Browsing History
Video available.
- https://www.youtube.com/watch?v=YY9ZV7Ma-gs
Web Search is increasingly entity-centric; as many common queries target specific entities, search results are progressively augmented with semi-structured and multimedia information about entities. However, search over personal Web browsing history still revolves around keyword-search mostly. B-hist aims at providing Web users with an effective tool for searching and accessing information previously looked up on the Web by providing multiple ways to filter results using temporal ranges, session-based clustering, and entity-centric search
TAER: Time Aware Entity Retrieval
Not running anymore.
- http://godzilla.kbs.uni-hannover.de:8080/TAER
This system allows to search the New York Times corpus in the period 1987-2006.
The user can provide a keyword query and select one article to read. Entities in the article are ranked according to their relevance to the user query.
SERWi: Semantic Entity Retrieval in Wikipedia
Not running anymore.
- http://serwi.L3S.uni-hannover.de/
This demo allows to run Entity Retrieval queries on top of the Wikipedia snapshot used at INEX XER 2007 and 2008.
The user can provide a keyword query describing the type of entities she wants (e.g., "countries where I can pay in Euro") and expect a ranked list of entities rapresented by their Wikipedia page
URI Match: Matching Semantic Web URIs
Not running anymore.
- http://urimatch.L3S.uni-hannover.de/
This demo, given two URIs, will tell the user whether they refer to the same real world entity or not. The system does not use the entity description rather it is purely based on the comparison of the URIs.
Finding Experts on the Semantic Desktop
Video available.
- http://www.youtube.com/watch?v=V6lfvxq2Bvo
This is a video of a prototype system developed within the Nepomuk project. The system allows to search for experts given a keyword query describing the topic of expertise. The candidate experts to be ranked and expertise evidence is extracted from the user desktop content.
ARES: A Retrieval Engine based on Sentiments
Not running anymore due to search API being shut down.
- http://ares.L3S.uni-hannover.de/
This demo allows to search the Web using three different commercial search engines. Retrieved pages are then classified according to the sentiment they express about the user query. The user is able either to see the original ranked list of results or to filter/reorder the list according to her needs
Vizio: A tool for Explorative Search
Not running anymore.
- http://vizio.L3S.uni-hannover.de/
This system allows to search the New York Times corpus in the period 1987-2006.
The user can provide a keyword query and select among different result visualization types (i.e., map, timeline, related words, person and places, and list).
Beagle++: Leveraging Personal Metadata for Desktop Search.
Video available.
- https://www.youtube.com/watch?v=Ui4GDkcR7-U
Beagle++ is an extensions to the Beagle search tool for the personal information space. Beagle++ now makes that search semantic, features you never experienced before. As a prototype it reflects current research activities towards the Semantic Desktop.
