Keynote Speakers

Social Media Analytics for Study of Public Events, User Mobility and Wellness

Abstract
Many people and organizations use multiple social networks to share their views and moments on many aspects of their activities. The mining of such contents along with their metadata (collectively known as the user generated contents or UGCs) enables us to study the various aspects of social habits, views, concerns and preferences of users. This talk describes the design, implementation and application of a live social observatory system. It incorporates an efficient and robust architecture to continually crawl live social streams from multiple social network sites and automatically analyzes theses streams to mine social senses, phenomena, influences and mobility trends. The Observatory can be used to study the evolution of public events, like an election, or personal events, like the health and activity timelines, demography and mobility of users. This talk describes a framework for such applications, and points towards long term research on collaborative live social observatories and the sharing of analytics.

Tat-Seng CHUA
Chair Professor School of Computing, National University of Singapore

Dr Chua is the KITHCT Chair Professor at the School of Computing, National University of Singapore. He was the Acting and Founding Dean of the School during 1998-2000. Dr Chua's main research interest is in multimedia information retrieval and social media analysis. In particular, his research focuses on the extraction, retrieval and question-answering (QA) of text, video and live media arising from the Web and social networks. He is the Director of a multi-million-dollar joint Center (named NExT) between NUS and Tsinghua University in China to develop technologies for live media search. The project aims to gather, mine, organize and retrieve user-generated contents.

Dr Chua is the 2015 winner of the prestigious ACM SIGMM award for Outstanding Technical Contributions to Multimedia Computing, Communications and Applications. He is the Chair of steering committee of ACM International Conference on Multimedia Retrieval (ICMR) and Multimedia Modeling (MMM) conference series. Dr Chua is also the General Co-Chair of ACM Multimedia 2005, ACM CIVR (now ACM ICMR) 2005, ACM SIGIR 2008, and ACM Web Science 2015. He serves in the editorial boards of 4 international journals. Dr Chua is the independent Director of a publicly listed company, and co-Founder of two technology startup companies in Singapore. He holds a PhD from the University of Leeds, UK.

Visualisation Techniques

Abstract. The human visual system has the ability to process a huge amount of data. It uses parallel processing and intelligent filter mechanisms to get an overview of the input data and detect interesting patterns at once.
Visualisation techniques use the power of the human visual system to convey a large amount of information rapidly.

This talk gives an overview of of visualisation techniques for low-dimensional and high-dimensional data. Examples will be used to demonstrate the underlying principles of visualisation techniques.

Christin Seifert
Chair of Media Computer Science at University of Passau, Germany.

Dr. Christin Seifert is a post-doctoral researcher at the University of Passau, Germany. She is currently leading a research group in the EU project EEXCESS. In her doctoral thesis at the University of Graz, Austria, she investigated the use of interactive visualisations for machine learning. She received her diploma from the University of Chemnitz, Germany, in the field of artificial intelligence.
She has been working at the Know-Center, Graz and Joanneum Research Graz from 2004 to 2012 in many nationally and internationally funded projects (MACS, Dyonipos, APOSDLE, MOBVIS).
Christin Seifert has published more than 70 peer-reviewed publications in the fields of machine learning, information visualisation, digital libraries and object recognition.

The current state of m-Health : Biomedical Engineering view

Introduction: what is m-Health and what are the main engineering problems to be solved.
Sensors - what physical principles are used to monitor physiological and biochemical parameters of humans. Flexible and non-contact sensors. New ideas for placing physiological monitors. Non-invasive sensors for glucose level monitoring.
Perspectives of implantable monitors. Mobile applications and their regulation.
Communicating technologies for transmitting data from m-health monitors to the cloud.
Role of smartphones and gate-ways in receiving and transmitting medical data to the cloud. New monitors with imbedded GSM modules.
Readiness of different countries in Europe to implement m-Health technologies. Market perspectives of m-Health.

Oleg Medvedev
Bauman Moscow Technical University, Fruct MD

Head, Working Group “Telemedicine and Health Remote Monitoring” of the Ministry of Health of the Russian Federation

Graduated from the I.Pavlov 1st Leningrad Medical Institute
Since 1992: Dean, Pharmacology Department, Fundamental Medicine Faculty, Lomonosov Moscow State University
During 10 years, he worked in the Institute of Pharmacology of the Academy of Medical Sciences and headed Pharmacology Department of the All-Union Cardiac Centre under the guidance of academician E.Chazov.
Oleg Medvedev’s scientific interests include pharmacology of cardiovascular system and antioxidants.
He authored over 200 publications in the leading national and foreign scientific journals. He renders joint research in USA, Japan, Germany, France, Australia and other countries.
Doctor of Medicine, Professor

A Cognitive Computing Approach to Natural Language Semantics

Abstract. In the past decades, the field of Computational Linguistics (CL) has been undergoing a steady shift away from rule-based, linguistically motivated modeling towards statistical learning and the induction of unsupervised feature representations. However, natural language components used in today’s CL pipelines are still static in the sense that their statistical model or rule-base is created once, then subsequently applied without further change. In this talk, I will motivate an adaptive approach to natural language semantics with different levels of adaptivity: In corpus adaptation, a prototypical conceptualization is induced from corpora and used as feature representation for machine learning tasks. In corpus- and text-adaptive approaches, this proto-conceptualization is contextualized to the current text at hand. Finally, in incremental learning approaches, the capability of the model to solve a particular task is iteratively improved through user interaction, adhering to the cognitive computing paradigm. The utility of these approaches is demonstrated in semantic tasks such as lexical substitution, word sense disambiguation, and paraphrasing, as well as in applications such as semantic search, question answering and a semantic writing aid. The utility of these approaches is demonstrated in semantic tasks such as lexical substitution, word sense disambiguation, and paraphrasing, as well as in applications such as semantic search, question answering and a semantic writing aid.

Chris Biemann
Assistant professor and head of the Language Technology group at TU Darmstadt, Germany.

Chris is assistant professor and head of the Language Technology group at TU Darmstadt in Germany. He received his Ph.D. from the University of Leipzig, and subsequently spent three years in industrial search engine research at Powerset and Microsoft Bing in San Francisco, California. He is regularly publishing in journals and top conferences in the field of Computational Linguistics.
His research is targeted towards self-learning structure from natural language text, specifically regarding semantic representations. Using big-data techniques, his group has built an open-source, scalable language-independent framework for symbolic distributional semantics. To connect induced structures to tasks, Chris is frequently using crowdsourcing techniques for the acquisition of natural language semantics data.

Crowdsourcing for Entity-Centric Information Access

Abstract. Crowdsourcing is a novel approach used to obtain data processing at scale. In this talk I will introduce the dynamics of crowdsourcing platforms and provide examples of their use to build hybrid human-machine systems. I will then present ZenCrowd: an hybrid system for entity linking and data integration problems over linked data showing how the use of human intelligence at scale in combination with machine-based algorithms outperforms traditional systems. Finally, we will also discuss how to use Linked Open Data on top of classic NLP pipelines for selecting entity types to support users browsing and reading Web pages.

Gianluca Demartini
Information School of the University of Sheffield, UK.

Dr. Gianluca Demartini is a Lecturer in Data Science at the Information School of the University of Sheffield, UK. Previously, he was post-doctoral researcher at the eXascale Infolab at the University of Fribourg, visiting researcher at UC Berkeley, junior researcher at the L3S Research Center, and intern at Yahoo! Research. He obtained a Ph.D. in Computer Science at the Leibniz University of Hannover in Germany focusing on entity-oriented search.
His research interests include Crowdsourcing for Human Computation, Information Retrieval, and Semantic Web. He has published more than 60 peer-reviewed scientific publications and given tutorials about Entity Retrieval and Crowdsourcing at international research conferences. He is editorial board member for the Journal of Web Semantics and has been program committee member for a number of international research conferences including SIGIR, ISWC, WWW, and CIKM.

Testimonies' evaluation in forensic practices: from polygraph to NLP

To detect deception in human interactions is a critical issue in police investigations. In the last 100 years, many approaches have been developed in order to unmask liars and lies. However, in spite of the great deal of effort of researchers and practitioners, to identify deceptive communications remains a very difficult task. The speech summarises the main approaches to deception detection, from the technologies for the exam of physiological variables to the analysis of non-verbal behavior.
The techniques employed for the testimonies' evaluation will be discussed as well, and particular relevance will be given to the application of NLP techniques, which rely on computational methods in order to analyze samples of spoken and written language, and in the last 10-15 have proven effective in a number of forensic applications, such as author profiling and deception detection.

Tommaso Fornaciari
Italian National Police

Tommaso Fornaciari is a Police Officer Psychologist of Italian National Police. Since 2003 he worked at the Forensic Science Police Service, dealing with crime scene analysis, behavioral analysis and investigative data analysis, mostly regarding bloody murders. With the purpose of supporting the analysis of testimonies, in 2009 he began to attend the PhD school of the Center for Mind/Brain Sciences - CIMeC of the University of Trento, where he carried out a research project in forensic linguistics (Ph.D. in Cognitive and Brain Sciences, 2012). In particular, he applied computational techniques in order to detect deception in transcripts of hearings held in Italian Courts. He is going ahead with research in deception detection and currently he works at the Italian Ministry of Interior, where he is engaged in research and technological innovation for public security.

From Uncovering to Promoting and
Exploiting Text Re-Use

Text re-use is “the situation in which pre-existing written material is consciously used again during the creation of a new text or version” (Clough, 2010). Plagiarism, the most (in)famous kind of text re-use, occurs when no credit is given to the author of an original ---borrowed--- material. In this talk I discuss four main topics: (i) the 3-axes strategy to discourage plagiarism in academia: prevention, surveillance, and response; (ii) the different mechanisms applied when borrowing a text, ranging from verbatim copy to translation; (iii) the computational models available to uncover (or not!) different types of borrowings; and (iv) a couple of scenarios in which text re-use (and its detection) is actually beneficial.

Alberto Barrón-Cedeño
Qatar Computing Research Institute

Alberto Barrón-Cedeño holds a PhD on Computer Science from Universitat Politènica de Valéncia. He is currently a Scientist at Qatar Computing Research Institute, HBKU. His current research is focused on the design of Natural Language Processing models to enhance community question answering fora, the analysis and exploitation of multilingual text resources, and the analysis of text re-use. He has 45+ publications in international journals and conferences on Natural Language Processing and Information Retrieval.