ESAIR 2015 - 8th Workshop on Exploiting Semantic Annotations for Information Retrieval

The amount of structured content published on the Web has been growing rapidly, making it possible to address increasingly complex information access tasks. Recent years have witnessed the emergence of large scale human-curated knowledge bases as well as a growing array of techniques that identify or extract information automatically from unstructured and semi-structured sources. Yet, the potential of rich document annotations cannot be fully realized when information needs are expressed only by short keyword queries. One main open research challenge, and opportunity, remains on the users’ side: how to encourage and allow searchers to articulate longer, semantically enriched queries? And, assuming users’ would be willing to provide additional details, what type of annotations would benefit retrieval systems the most?
The ESAIR workshop series aims to advance the general research agenda on this core problem. The eighth edition of ESAIR, with a renewed set of organizers, sets its focus on applications. We invite presentations of prototype systems in a dedicated “Annotations in Action” demo track, in addition to the regular research and position paper contributions. The desired result of the workshop is a roadmap and research agenda that guides academic efforts and aligns them with industrial directions and developments.
SCOPE AND TOPICS
The workshop will bring together researchers working with semantic annotations, its use cases, its sources, its users, and its use in DB, IR, KM, or Web research, and work together on a range of open questions. Annotations come in a variety of flavors (named entities, temporal information, geo-positional markers, semantic roles, sentiment, etc.) and there is a growing repertoire of tools and techniques available for extracting these annotations automatically from text. The question then presents itself: what, if anything, is missing? We seek to answer this question by focusing on applications that are rooted in specific, real-world use cases.
Topics for the workshop include, but are not limited to:
Applications and use cases
What are use cases that make obvious the need for semantic annotation of information?
What tasks cannot be solved by traditional (bag-of-words) retrieval approaches?
Annotations
What types of annotation are available and what is missing?
Are there crucial differences between human and machine-generated annotations?
How should we deal with the uncertainty of annotations?
User interfaces and interaction
How to aid users in articulating powerful queries (beyond a few keywords)?
How to present results and interact with users in an intelligible way?
Evaluation
How to evaluate semantic annotations (component-based vs. end-to-end)?