We increasingly live our life online. Information is accumulated on a
wide range of human activities, from science and facts, to personal
content, opinions, and trends. Across the globe, people’s knowledge,
experiences and interactions effortlessly find their way to online
outlets, alongside traditional edited content, ready to be shared with
millions. LiMoSINe will integrate the research activities of leading
researchers across diverse topics with a view to enabling new kinds of
language-based search technology. The LiMoSINe vision is to transition
access to online information from a document-centric search paradigm
focused on returning disconnected atomic pieces to a truly semantic
aggregation paradigm. In this new paradigm, machines will understand a
user’s intent, discover and organize facts, identify opinions,
experiences and trends, all from inherently multilingual online
sources and open knowledge repositories. LiMoSINe’s aggregation
engines will automatically organize search results in semantically
meaningful ways. LiMoSINe has the following objectives: To enable
semantically structured access to multi-lingual online content; To
integrate deep linguistic processing in information extraction; To
support semantic mining where data-driven patterns are made human
interpretable using the web of data; To develop evaluation methods for
rigorously assessing the effectiveness of semantic search and semantic
aggregation in a lab-based setting; To exploit its research results in
three demanding multilingual use cases: (i) open-domain community
question answering, (ii) online reputation management in a
professional task-based setting, and (iii) intelligent content
annotation and search on a photo-sharing platform. The components of
LiMoSINe will be integrated through web services with solutions
currently in place at the project’s use case owners.