Collaboration Agreement between TRENDMINER and META-NET

The Network of Excellence “Technologies for the Multilingual European Information Society”, henceforth META-NET, and the Strep project “Large-scale, Cross-lingual Trend Mining and Summarisation of Real-time Media Streams”, henceforth TrendMiner, both established within Framework Programme 7, recognise the complementarity of their objectives and declare their intent for multi-level collaboration.

Scope and Objectives of the Participants

The TrendMiner project aims at delivering innovative, portable open-source real-time methods for cross-lingual mining and summarisation of large-scale stream media. TrendMiner will achieve this through an inter-disciplinary approach, combining deep linguistic methods from text processing, knowledge-based reasoning from web science, machine learning, economics, and political science. No expensive human annotated data will be required due to our use of time-series data (e.g. financial markets, political polls) as a proxy. A key novelty will be weakly supervised machine learning algorithms for automatic discovery of new trends and correlations. Scalability and affordability will be addressed through a cloud-based infrastructure for real-time text mining from stream media.  Results will be validated in two high-profile case studies: financial decision support (with analysts, traders, regulators, and economists) and political analysis and monitoring (with politicians, economists, and political journalists).

META-NET is a Network of Excellence dedicated to the technological foundations of the European multilingual information society. Its main goals are: to build a strategic alliance, consisting of national and international research programmes, corporate users and commercial technology providers and language communities; to strengthen the European research community through research networking and by creating new schemes and structures for sharing resources, that is the META-SHARE infrastructure; and to build bridges by approaching open problems in collaboration with other research fields such as machine learning, social computing, cognitive systems, knowledge technologies and multimedia content. META-NET will lead to a strong language technology community with ties to other R&D communities, with a network into industry and public administration, and with visions and plans for a strategic research agenda, to support the sustainability of the European, multilingual information society.

Areas of collaboration

TrendMiner will both collect and generate a huge amount of language data dealing with opinion, sentiments and trend. Existing HLT tools will be adapted or new tools will be developed, with the goal of analysis the media stream. TrendMiner sees a specific synergy with META-NET and also META-SHARE on this issue of language resources. In order to create synergies in these areas, both projects agree to the following:

• TrendMiner will actively participate in and exhibit at major events with common outreach goals, e.g. META-FORUM;

• TrendMiner will promote META through its various dissemination channels and materials;

• TrendMiner will provide access to its tools and data resources via the META-SHARE infrastructure, in addition to the project specific dissemination channels.