Important Dates
Conference Programme
Organising Committee
Programme Committee
Invited Speakers
Industry Forum
Accepted Papers
Accepted Demos
Accepted Posters
Call for Papers [closed]
Call for Posters/Demos
Submissions [secure]
Download Poster
Download Flyer
[colour] [black & white]
  Invited Speakers  
Harmelen   Frank van Harmelen
Vrije Universiteit Amsterdam

[Download Presentation]

Where does it break? or: Why the Semantic Web is not just "research as usual"


Work on the Semantic Web is all to often phrased as a technological challenge: how to improve the precision of search engines, how to personalise web-sites, how to integrate weakly-structured data-sources, etc. This suggests that we will be able to realise the Semantic Web by merely applying (and at most refining) the results that are already available from many branches of Computer Science.

I will argue in this talk that instead of (just) a technological challenge, the Semantic Web forces us to rethink the foundations of many subfields of Computer Science. This is certainly true for my own field (Knowledge Representation), where the challenge of the Semantic Web continues to break many often silently held and shared assumptions underlying decades of research. With some caution, I claim that this is also true for other fields, such as Machine Learning, Natural Language Processing, Databases, and others. For each of these fields, I will try to identify silently held assumptions which are no longer true on the Semantic Web, prompting a radical rethink of many past results from these fields.


Frank van Harmelen is professor in Knowledge Representation and Reasoning at the Vrije Universiteit Amsterdam, with a PhD from the strategies for theorem provers and on formal foundations of knowledge modelling, he has been very active in recent years in developments around the Semantic Web. One of his five books is the first text book on Semantic Web technology. He is involved in numerous European Semantic Web projects, and he was one of the designers of the W3C standard ontology language OWL. He was the Program Chair of the ECAI 2002, the General Chair of the 2004 International Semantic Web Conference, and the chair the Semantic Web track of the 2005 World Wide Web conference

Hovy   Eduard Hovy
Information Sciences Institute
University of Southern California


Toward large-scale shallow semantics for higher-quality NLP
[Download Presentation]


Building on the successes of the past decade’s work on statistical methods, there are signs that continued quality improvement for QA, summarization, information extraction, and possibly even machine translation require more-elaborate and possibly even (shallow) semantic representations of text meaning.

But how can one define a large-scale shallow semantic representation system and contents adequate for NLP applications, and how can one create the corpus of shallow semantic representation structures that would be required to train machine learning algorithms? This talk addresses the components required (including a symbol definition ontology and a corpus of (shallow) meaning representations) and the resources and methods one needs to build them (including existing ontologies, human annotation procedures, and a verification methodology). To illustrate these aspects, several existing and recent projects and applicable resources are described, and a research programme for the near future is outlined. Should NLP be willing to face this challenge, we may in the not-too-distant future find ourselves working with a whole new order of knowledge, namely (shallow) and doing so in increasing collaboration (after a 40-years separation) with specialists from the Knowledge Representation and reasoning community.

Speaker's Bio

Eduard Hovy (http://www.isi.edu/~hovy.html) directs the Natural Language Research Group at the Information Sciences Institute of the University of Southern California. He is also Deputy Director of the Intelligent Systems Division, as well as a research associate professor of the Computer Science Department of USC and Advisory Professor of the Beijing University of Posts and Telecommunications. His research focuses on information extraction, automated text summarization, question answering, the semi-automated construction of large lexicons and ontologies, machine translation, and digital government. In the pre-semantic web, googling "Hovy" produces some "blue" in Guarani, one of the two official languages of Paraguay.

Jameson   Anthony Jameson
DFKI and International University in Germany

[Download Presentation]

Usability and the Semantic Web


In addition to its technical implications, the semantic web vision gives rise to some challenges concerning usability and interface design. What difficulties can arise when persons with little or no relevant training try to (a) formulate knowledge (e.g., with ontology editors or annotation tools) in such a way that it can be exploited by semantic web technologies; or (b) leverage semantic information while querying or browsing?

What strategies have been applied in an effort to overcome these difficulties, and what are the main open issues that remain? This talk will address these questions, referring to examples and results from a variety of research efforts, including the project SemIPort, which concerns semantic methods and tools for information portals, and Halo 2, in which tools have been developed and evaluated that enable scientists to formalize and query college-level scientific knowledge.

Speaker's Bio

Anthony Jameson is principal researcher at DFKI, the German Research Center for Artificial Intelligence, and adjunct professor for human-computer interaction at the International University in Germany. According to CiteSeer, A. Jameson is among the top 1% of computer science authors in terms of citations; having been cited more often than A. Turing; the ontological status of the other 99% of the authors is largely unknown. His web homepage sometimes appears among Google's top 10 search results for the name "Jameson", despite competition from an Irish whiskey, a hotel chain, a Marxist political and literary critic, and a pseudonymous actress/model. The number of web pages that mention his name, in whole or in part, exceeds 123,000,000, which is one of the largest numbers ever mentioned in a speaker's bio.